The Visual Guide on How Neural Networks Learn from Data

  • Course provided by Udemy
  • Study type: Online
  • Starts: Anytime
  • Price: See latest price on Udemy
Udemy

Course Description

Course Achievements (January 2021):

  • +3,100 Worldwide Students enrolled

  • Trophy Awards for Key Section Achievements!

═════════════════════════════════════════════════════

Some Student Reviews are:

"This is an excellent course for people who wish to get an introductory experience in learning about Neural Networks." (December 2020).

"This is a very good introduction on how ANN work. It helps build intuition both on the backpropagation and the math behind it." (January 2020).

"This course does what it claims to do very well." (October 2019)

"Very structured and logical" (July 2018).

"Enlightening overview of how neural networks operate mathematically." (March 2018).

"I just loved this course. The course is very well taught and is divided in easy-to-digest units." (December 2017).

═════════════════════════════════════════════════════

Hi. Thanks for showing interest in this course!

What makes this course special:

  • Step-by-Step Neural Network Learning Process,

  • Master topics like Fundamentals, Objectives, Required Datasets, Weights, Biases, Nodes, Activation functions, Feed-Forward Passes, Predictions, Losses, Gradient Descent, Learning, Backpropagation and more!

  • Plus, personalized feedback and help. You ask, I answer directly!


This is your BEST resource for Neural Networks (NN) learning! A must for understanding special concepts and not get lost in computing your own NNs:


✅ First:

You'll start the Neural Networks Primer with Fundamentals, Objectives, Data and more:

  • Learn concepts using analogies for maximum learning, so you will be fully covered.

  • Learning how NNs learn will be easy with this Primer under your sleeve!



✅ Second:

You'll continue the NN Primer with Learning, Backpropagation and Predictions and more topics

  • In an easy and intuitive way, you will understand how they work,

  • This is fundamental in the NN Learning Process.

  • At the end of this section, you will have mastered the NN Primer!

  • Now, you are ready for the Step-by-Step (in-Motion) sections!



✅ Third:

You'll start the in-Motion section with Inputs, Weights, Biases, Activations, Nodes and Feed-Forward Passes:

  • See how they work inside an NN,

  • Step-by-step templates, so you can follow every detail,

  • These files will be dynamic, so you'll understand how NNs work as numbers will be updated on-the-fly and right in front of your eyes.


✅ Forth:

You'll continue with the in-Motion section with NN Learning, Backpropagation, Tuning and Prediction:

  • You will understand how NNs learn from the data.

  • This all part of the dynamic templates you get to keep.

  • You'll do several examples along the way for maximum learning.

  • Lastly, you'll see what NNs do to make the best predictions.


✅ Fifth:

You'll finish the in-Motion section by doing a complete rundown on everyting you've learned so far:

  • You'll see how all NN inner components work for learning and prediction.

  • Pay close attention at how all parts adjust, making the NN learn in front of your eyes.

  • After this section, you will be fully versed on how NNs learn!


✅ Sixth:

I will devote a section for more additional knowledge and resources for continous learning. And then, I will conclude with some Final Words.


What are the Requirements?

  • The only thing you'll need for this course is: Excel and PowerPoint: It is that easy!

  • You will also need to bring your Basic Maths too,

  • If you bring your Calculus (Derivatives) knowledge, that will be a big plus for you (but not required),


What are some of the Benefits?

  • As it is usual in my courses, you will get all files and spreadsheets for all lectures.

  • This way you can replicate everything I do immediately after each lecture.

  • Neural Networks are the new thing today.

  • With it, you can explore and engage Artificial Intelligence, which I recommend you to dive in as it's part of the future.

  • Plus, it's very rewarding and fun too!

  • New content coming in the near future, let me know yout thoughts.


Lastly, you can post questions or doubts, and I’ll answer to you personally.

I hope you find this course as useful as I have creating it!


I’ll see you inside,


-M.A. Mauricio M.

Who this course is for:

  • Once and For All => Learn and Understand Step-by-Step How Neural Networks work with this course

Instructor

+10,000 students and growing!
  • 4.4 Instructor Rating
  • 1,428 Reviews
  • 11,088 Students
  • 4 Courses

Mauricio Maroto holds a Master degree in Industrial Economics from Carlos III University (Madrid, Spain).

With more than 8 years of professional experience, he's always been involved in creating insights for strategic decision making through data analysis.

From data query, cleaning and processing, to clustering, regression and classification techniques, Mauricio is passionate about finding patterns and trends in large datasets.

Mauricio's other passions are his family, friends, his pets and he loves to play soccer, whether indoors or outdoors. He also goes out for a run on weekends (not lately). He also loves topics such as Economics, Programming and Science.

Expected Outcomes

  1. Understand what Neural Networks (NNs) are all about Step-by-Step in-Motion NN files for you to KEEP, yes, these files are yours! Adjust Templates to your requirements => SEE what's going on inside NNs! See how Neural Networks LEARN (graphic and dynamic files), follow all causes and effects! Understand KEY ALGORITHMS in NN's (Gradient Descent, Backpropagation and more) Know Types of Neural Networks, Designs and Advanced Topics Course content 8 sections • 56 lectures • 2h 47m total length Expand all sections Introduction 4 lectures • 2min A foreword and Initial Tips 01:16 How to go through this course 00:32 BONUS COUPON: For any course! 00:04 General Note 00:04 Neural Networks PRIMER: Fundamentals, Objective and Data and more 6 lectures • 33min Fundamental Parts of any NEURAL NETWORK Preview 05:18 Debunking Myths and Thruths Preview 08:15 Our first graphic NEURAL NETWORK 05:07 What is the objective of a NEURAL NETWORK? 04:56 What type of data is good for NEURAL NETWORKS? 03:49 What are Training, Validation and Test datasets? 05:24 Quiz 6 questions Neural Networks PRIMER: Learning, Overfitting and Prediction and more 7 lectures • 26min What's a Feed-Forward Pass (FFP)? 07:42 What are Epochs? 02:54 How good are NEURAL NETWORKS at Prediction? 04:05 Quick Exercise 1 00:10 How do NEURAL NETWORKS Learn? 05:38 What types of NEURAL NETWORKS are out there? 05:18 Quiz 4 questions 1st Trophy Achieved 00:05 Neural Networks IN-MOTION: Inputs, Weights, Biases, Activations and Predictions 12 lectures • 30min Preview 1 Preview 01:05 How do Inputs (x) look like? 02:38 How do Nodes (n) look like? 03:18 How do Weights (w) look like? And how to initialize them 05:17 A Quick Note 1 00:09 How do Biases (b) look like? 01:38 How do Activation functions (f) look like? 03:28 How do Activation functions Derivative (f') look like? 04:11 FFP: from Inputs to Nodes 1 and 2 05:01 FFP: from Nodes 1,2 to Node 3 (Prediction output) 03:28 Quick Exercise 2 00:04 Quiz 6 questions 2nd Trophy Achieved 00:04 Neural Networks IN-MOTION: Losses, Backpropagation, Learning and Tuning 16 lectures • 55min Preview 2 Preview 01:16 What's the Loss associated? 06:32 Quick Exercise 3 00:05 Set an initial Learning Rate 02:20 Gradient Descent and Backpropagation 06:04 Deriving Formulas for Node 3 (Optional) 07:19 Backpropagation: Computing Change at Node 3 03:20 Deriving Formulas for Node 1 (Optional) 05:48 Backpropagation: Computing Change at Node 1 04:24 Deriving Formulas for Node 2 (Optional) 01:54 Backpropagation: Computing Change at Node 2 02:21 3rd Trophy Achieved 00:07 Let the Neural Network Learn 06:12 Compare new Results by Learning 02:32 Let the Neural Network Learn more and Compare 05:03 4th Trophy Achieved 00:07 Quiz 5 questions Neural Networks IN-MOTION: Complete Rundown of NN Learning 9 lectures • 20min The Prediction (Y^) and Loss (L) 06:44 Quick Exercise 4 00:10 The Weights (w) 04:28 Quick Exercise 5 00:12 The Biases (b) 03:02 Quick Exercise 6 00:12 Quick Exercise 7 00:06 Complete NN Rundown 04:57 5th Trophy Achieved 00:07 Neural Networks: Further Knowledge 1 lecture • 1min Further Knowledge is here 00:08 Final Words 1 lecture • 1min Final Words 00:29 Requirements 1. Excel and PowerPoint (Office 2010+) 2. Maths (Basics) 3. A Plus: Calculus and Derivatives (Optional, not required) Description Course Achievements (January 2021): +3,100 Worldwide Students enrolled Trophy Awards for Key Section Achievements! ═════════════════════════════════════════════════════ Some Student Reviews are: "This is an excellent course for people who wish to get an introductory experience in learning about Neural Networks." (December 2020). "This is a very good introduction on how ANN work. It helps build intuition both on the backpropagation and the math behind it." (January 2020). "This course does what it claims to do very well." (October 2019) "Very structured and logical" (July 2018). "Enlightening overview of how neural networks operate mathematically." (March 2018). "I just loved this course. The course is very well taught and is divided in easy-to-digest units." (December 2017). ═════════════════════════════════════════════════════ Hi. Thanks for showing interest in this course! What makes this course special: Step-by-Step Neural Network Learning Process, Master topics like Fundamentals, Objectives, Required Datasets, Weights, Biases, Nodes, Activation functions, Feed-Forward Passes, Predictions, Losses, Gradient Descent, Learning, Backpropagation and more! Plus, personalized feedback and help. You ask, I answer directly! This is your BEST resource for Neural Networks (NN) learning! A must for understanding special concepts and not get lost in computing your own NNs: ✅ First: You'll start the Neural Networks Primer with Fundamentals, Objectives, Data and more: Learn concepts using analogies for maximum learning, so you will be fully covered. Learning how NNs learn will be easy with this Primer under your sleeve! ✅ Second: You'll continue the NN Primer with Learning, Backpropagation and Predictions and more topics In an easy and intuitive way, you will understand how they work, This is fundamental in the NN Learning Process. At the end of this section, you will have mastered the NN Primer! Now, you are ready for the Step-by-Step (in-Motion) sections! ✅ Third: You'll start the in-Motion section with Inputs, Weights, Biases, Activations, Nodes and Feed-Forward Passes: See how they work inside an NN, Step-by-step templates, so you can follow every detail, These files will be dynamic, so you'll understand how NNs work as numbers will be updated on-the-fly and right in front of your eyes. ✅ Forth : You'll continue with the in-Motion section with NN Learning, Backpropagation, Tuning and Prediction: You will understand how NNs learn from the data. This all part of the dynamic templates you get to keep. You'll do several examples along the way for maximum learning. Lastly, you'll see what NNs do to make the best predictions. ✅ Fifth: You'll finish the in-Motion section by doing a complete rundown on everyting you've learned so far: You'll see how all NN inner components work for learning and prediction. Pay close attention at how all parts adjust, making the NN learn in front of your eyes. After this section, you will be fully versed on how NNs learn! ✅ Sixth: I will devote a section for more additional knowledge and resources for continous learning. And then, I will conclude with some Final Words . What are the Requirements ? The only thing you'll need for this course is: Excel and PowerPoint: It is that easy! You will also need to bring your Basic Maths too, If you bring your Calculus (Derivatives) knowledge, that will be a big plus for you (but not required), What are some of the Benefits ? As it is usual in my courses, you will get all files and spreadsheets for all lectures. This way you can replicate everything I do immediately after each lecture. Neural Networks are the new thing today. With it, you can explore and engage Artificial Intelligence, which I recommend you to dive in as it's part of the future. Plus, it's very rewarding and fun too! New content coming in the near future, let me know yout thoughts. Lastly, you can post questions or doubts, and I’ll answer to you personally. I hope you find this course as useful as I have creating it! I’ll see you inside, -M.A. Mauricio M. Who this course is for: Once and For All => Learn and Understand Step-by-Step How Neural Networks work with this course Show more Show less Instructor Mauricio Maroto +10,000 students and growing! 4.4 Instructor Rating 1,428 Reviews 11,088 Students 4 Courses Mauricio Maroto holds a Master degree in Industrial Economics from Carlos III University (Madrid, Spain). With more than 8 years of professional experience, he's always been involved in creating insights for strategic decision making through data analysis. From data query, cleaning and processing, to clustering, regression and classification techniques, Mauricio is passionate about finding patterns and trends in large datasets. Mauricio's other passions are his family, friends, his pets and he loves to play soccer, whether indoors or outdoors. He also goes out for a run on weekends (not lately). He also loves topics such as Economics, Programming and Science. Show more Show less Udemy Business Teach on Udemy Get the app About us Contact us Careers Blog Help and Support Affiliate Impressum Kontakt Terms Privacy policy Cookie settings Sitemap © 2021 Udemy, Inc. window.handleCSSToggleButtonClick = function (event) { var target = event.currentTarget; var cssToggleId = target && target.dataset && target.dataset.cssToggleId; var input = cssToggleId && document.getElementById(cssToggleId); if (input) { if (input.dataset.type === 'checkbox') { input.dataset.checked = input.dataset.checked ? '' : 'checked'; } else { input.dataset.checked = input.dataset.allowToggle && input.dataset.checked ? '' : 'checked'; var radios = document.querySelectorAll('[name="' + input.dataset.name + '"]'); for (var i = 0; i (function(){window['__CF$cv$params']={r:'67783a15ae63e658',m:'84b422edecc6e436e3c051b540bd28e8a413122c-1627749191-1800-AYx94i1oVJqv++aLhz7X3pu/ShuDb+3GFEVrbWvJUWzLu9EA2zgQJb2KJ9rrUYRLlgZ3D45MjUnwwlIb5uxYQMPBcvasT8bf3KgA52Ab8IUBfTwYLQdjg/Rj8T4DNc1VL3TE63Ce+Df50IqFuUNExEnIhu3/aFFAi0je3yKW41HFduE+0ZBibqxE46hnKYX3+U6+EjO5n98hrnwNMkFzlv0=',s:[0x4e312ac39e,0xff1bf5214f],}})();
  2. Step-by-Step in-Motion NN files for you to KEEP, yes, these files are yours! Adjust Templates to your requirements => SEE what's going on inside NNs! See how Neural Networks LEARN (graphic and dynamic files), follow all causes and effects! Understand KEY ALGORITHMS in NN's (Gradient Descent, Backpropagation and more) Know Types of Neural Networks, Designs and Advanced Topics Course content 8 sections • 56 lectures • 2h 47m total length Expand all sections Introduction 4 lectures • 2min A foreword and Initial Tips 01:16 How to go through this course 00:32 BONUS COUPON: For any course! 00:04 General Note 00:04 Neural Networks PRIMER: Fundamentals, Objective and Data and more 6 lectures • 33min Fundamental Parts of any NEURAL NETWORK Preview 05:18 Debunking Myths and Thruths Preview 08:15 Our first graphic NEURAL NETWORK 05:07 What is the objective of a NEURAL NETWORK? 04:56 What type of data is good for NEURAL NETWORKS? 03:49 What are Training, Validation and Test datasets? 05:24 Quiz 6 questions Neural Networks PRIMER: Learning, Overfitting and Prediction and more 7 lectures • 26min What's a Feed-Forward Pass (FFP)? 07:42 What are Epochs? 02:54 How good are NEURAL NETWORKS at Prediction? 04:05 Quick Exercise 1 00:10 How do NEURAL NETWORKS Learn? 05:38 What types of NEURAL NETWORKS are out there? 05:18 Quiz 4 questions 1st Trophy Achieved 00:05 Neural Networks IN-MOTION: Inputs, Weights, Biases, Activations and Predictions 12 lectures • 30min Preview 1 Preview 01:05 How do Inputs (x) look like? 02:38 How do Nodes (n) look like? 03:18 How do Weights (w) look like? And how to initialize them 05:17 A Quick Note 1 00:09 How do Biases (b) look like? 01:38 How do Activation functions (f) look like? 03:28 How do Activation functions Derivative (f') look like? 04:11 FFP: from Inputs to Nodes 1 and 2 05:01 FFP: from Nodes 1,2 to Node 3 (Prediction output) 03:28 Quick Exercise 2 00:04 Quiz 6 questions 2nd Trophy Achieved 00:04 Neural Networks IN-MOTION: Losses, Backpropagation, Learning and Tuning 16 lectures • 55min Preview 2 Preview 01:16 What's the Loss associated? 06:32 Quick Exercise 3 00:05 Set an initial Learning Rate 02:20 Gradient Descent and Backpropagation 06:04 Deriving Formulas for Node 3 (Optional) 07:19 Backpropagation: Computing Change at Node 3 03:20 Deriving Formulas for Node 1 (Optional) 05:48 Backpropagation: Computing Change at Node 1 04:24 Deriving Formulas for Node 2 (Optional) 01:54 Backpropagation: Computing Change at Node 2 02:21 3rd Trophy Achieved 00:07 Let the Neural Network Learn 06:12 Compare new Results by Learning 02:32 Let the Neural Network Learn more and Compare 05:03 4th Trophy Achieved 00:07 Quiz 5 questions Neural Networks IN-MOTION: Complete Rundown of NN Learning 9 lectures • 20min The Prediction (Y^) and Loss (L) 06:44 Quick Exercise 4 00:10 The Weights (w) 04:28 Quick Exercise 5 00:12 The Biases (b) 03:02 Quick Exercise 6 00:12 Quick Exercise 7 00:06 Complete NN Rundown 04:57 5th Trophy Achieved 00:07 Neural Networks: Further Knowledge 1 lecture • 1min Further Knowledge is here 00:08 Final Words 1 lecture • 1min Final Words 00:29 Requirements 1. Excel and PowerPoint (Office 2010+) 2. Maths (Basics) 3. A Plus: Calculus and Derivatives (Optional, not required) Description Course Achievements (January 2021): +3,100 Worldwide Students enrolled Trophy Awards for Key Section Achievements! ═════════════════════════════════════════════════════ Some Student Reviews are: "This is an excellent course for people who wish to get an introductory experience in learning about Neural Networks." (December 2020). "This is a very good introduction on how ANN work. It helps build intuition both on the backpropagation and the math behind it." (January 2020). "This course does what it claims to do very well." (October 2019) "Very structured and logical" (July 2018). "Enlightening overview of how neural networks operate mathematically." (March 2018). "I just loved this course. The course is very well taught and is divided in easy-to-digest units." (December 2017). ═════════════════════════════════════════════════════ Hi. Thanks for showing interest in this course! What makes this course special: Step-by-Step Neural Network Learning Process, Master topics like Fundamentals, Objectives, Required Datasets, Weights, Biases, Nodes, Activation functions, Feed-Forward Passes, Predictions, Losses, Gradient Descent, Learning, Backpropagation and more! Plus, personalized feedback and help. You ask, I answer directly! This is your BEST resource for Neural Networks (NN) learning! A must for understanding special concepts and not get lost in computing your own NNs: ✅ First: You'll start the Neural Networks Primer with Fundamentals, Objectives, Data and more: Learn concepts using analogies for maximum learning, so you will be fully covered. Learning how NNs learn will be easy with this Primer under your sleeve! ✅ Second: You'll continue the NN Primer with Learning, Backpropagation and Predictions and more topics In an easy and intuitive way, you will understand how they work, This is fundamental in the NN Learning Process. At the end of this section, you will have mastered the NN Primer! Now, you are ready for the Step-by-Step (in-Motion) sections! ✅ Third: You'll start the in-Motion section with Inputs, Weights, Biases, Activations, Nodes and Feed-Forward Passes: See how they work inside an NN, Step-by-step templates, so you can follow every detail, These files will be dynamic, so you'll understand how NNs work as numbers will be updated on-the-fly and right in front of your eyes. ✅ Forth : You'll continue with the in-Motion section with NN Learning, Backpropagation, Tuning and Prediction: You will understand how NNs learn from the data. This all part of the dynamic templates you get to keep. You'll do several examples along the way for maximum learning. Lastly, you'll see what NNs do to make the best predictions. ✅ Fifth: You'll finish the in-Motion section by doing a complete rundown on everyting you've learned so far: You'll see how all NN inner components work for learning and prediction. Pay close attention at how all parts adjust, making the NN learn in front of your eyes. After this section, you will be fully versed on how NNs learn! ✅ Sixth: I will devote a section for more additional knowledge and resources for continous learning. And then, I will conclude with some Final Words . What are the Requirements ? The only thing you'll need for this course is: Excel and PowerPoint: It is that easy! You will also need to bring your Basic Maths too, If you bring your Calculus (Derivatives) knowledge, that will be a big plus for you (but not required), What are some of the Benefits ? As it is usual in my courses, you will get all files and spreadsheets for all lectures. This way you can replicate everything I do immediately after each lecture. Neural Networks are the new thing today. With it, you can explore and engage Artificial Intelligence, which I recommend you to dive in as it's part of the future. Plus, it's very rewarding and fun too! New content coming in the near future, let me know yout thoughts. Lastly, you can post questions or doubts, and I’ll answer to you personally. I hope you find this course as useful as I have creating it! I’ll see you inside, -M.A. Mauricio M. Who this course is for: Once and For All => Learn and Understand Step-by-Step How Neural Networks work with this course Show more Show less Instructor Mauricio Maroto +10,000 students and growing! 4.4 Instructor Rating 1,428 Reviews 11,088 Students 4 Courses Mauricio Maroto holds a Master degree in Industrial Economics from Carlos III University (Madrid, Spain). With more than 8 years of professional experience, he's always been involved in creating insights for strategic decision making through data analysis. From data query, cleaning and processing, to clustering, regression and classification techniques, Mauricio is passionate about finding patterns and trends in large datasets. Mauricio's other passions are his family, friends, his pets and he loves to play soccer, whether indoors or outdoors. He also goes out for a run on weekends (not lately). He also loves topics such as Economics, Programming and Science. Show more Show less Udemy Business Teach on Udemy Get the app About us Contact us Careers Blog Help and Support Affiliate Impressum Kontakt Terms Privacy policy Cookie settings Sitemap © 2021 Udemy, Inc. window.handleCSSToggleButtonClick = function (event) { var target = event.currentTarget; var cssToggleId = target && target.dataset && target.dataset.cssToggleId; var input = cssToggleId && document.getElementById(cssToggleId); if (input) { if (input.dataset.type === 'checkbox') { input.dataset.checked = input.dataset.checked ? '' : 'checked'; } else { input.dataset.checked = input.dataset.allowToggle && input.dataset.checked ? '' : 'checked'; var radios = document.querySelectorAll('[name="' + input.dataset.name + '"]'); for (var i = 0; i (function(){window['__CF$cv$params']={r:'67783a15ae63e658',m:'84b422edecc6e436e3c051b540bd28e8a413122c-1627749191-1800-AYx94i1oVJqv++aLhz7X3pu/ShuDb+3GFEVrbWvJUWzLu9EA2zgQJb2KJ9rrUYRLlgZ3D45MjUnwwlIb5uxYQMPBcvasT8bf3KgA52Ab8IUBfTwYLQdjg/Rj8T4DNc1VL3TE63Ce+Df50IqFuUNExEnIhu3/aFFAi0je3yKW41HFduE+0ZBibqxE46hnKYX3+U6+EjO5n98hrnwNMkFzlv0=',s:[0x4e312ac39e,0xff1bf5214f],}})();
  3. Adjust Templates to your requirements => SEE what's going on inside NNs! See how Neural Networks LEARN (graphic and dynamic files), follow all causes and effects! Understand KEY ALGORITHMS in NN's (Gradient Descent, Backpropagation and more) Know Types of Neural Networks, Designs and Advanced Topics Course content 8 sections • 56 lectures • 2h 47m total length Expand all sections Introduction 4 lectures • 2min A foreword and Initial Tips 01:16 How to go through this course 00:32 BONUS COUPON: For any course! 00:04 General Note 00:04 Neural Networks PRIMER: Fundamentals, Objective and Data and more 6 lectures • 33min Fundamental Parts of any NEURAL NETWORK Preview 05:18 Debunking Myths and Thruths Preview 08:15 Our first graphic NEURAL NETWORK 05:07 What is the objective of a NEURAL NETWORK? 04:56 What type of data is good for NEURAL NETWORKS? 03:49 What are Training, Validation and Test datasets? 05:24 Quiz 6 questions Neural Networks PRIMER: Learning, Overfitting and Prediction and more 7 lectures • 26min What's a Feed-Forward Pass (FFP)? 07:42 What are Epochs? 02:54 How good are NEURAL NETWORKS at Prediction? 04:05 Quick Exercise 1 00:10 How do NEURAL NETWORKS Learn? 05:38 What types of NEURAL NETWORKS are out there? 05:18 Quiz 4 questions 1st Trophy Achieved 00:05 Neural Networks IN-MOTION: Inputs, Weights, Biases, Activations and Predictions 12 lectures • 30min Preview 1 Preview 01:05 How do Inputs (x) look like? 02:38 How do Nodes (n) look like? 03:18 How do Weights (w) look like? And how to initialize them 05:17 A Quick Note 1 00:09 How do Biases (b) look like? 01:38 How do Activation functions (f) look like? 03:28 How do Activation functions Derivative (f') look like? 04:11 FFP: from Inputs to Nodes 1 and 2 05:01 FFP: from Nodes 1,2 to Node 3 (Prediction output) 03:28 Quick Exercise 2 00:04 Quiz 6 questions 2nd Trophy Achieved 00:04 Neural Networks IN-MOTION: Losses, Backpropagation, Learning and Tuning 16 lectures • 55min Preview 2 Preview 01:16 What's the Loss associated? 06:32 Quick Exercise 3 00:05 Set an initial Learning Rate 02:20 Gradient Descent and Backpropagation 06:04 Deriving Formulas for Node 3 (Optional) 07:19 Backpropagation: Computing Change at Node 3 03:20 Deriving Formulas for Node 1 (Optional) 05:48 Backpropagation: Computing Change at Node 1 04:24 Deriving Formulas for Node 2 (Optional) 01:54 Backpropagation: Computing Change at Node 2 02:21 3rd Trophy Achieved 00:07 Let the Neural Network Learn 06:12 Compare new Results by Learning 02:32 Let the Neural Network Learn more and Compare 05:03 4th Trophy Achieved 00:07 Quiz 5 questions Neural Networks IN-MOTION: Complete Rundown of NN Learning 9 lectures • 20min The Prediction (Y^) and Loss (L) 06:44 Quick Exercise 4 00:10 The Weights (w) 04:28 Quick Exercise 5 00:12 The Biases (b) 03:02 Quick Exercise 6 00:12 Quick Exercise 7 00:06 Complete NN Rundown 04:57 5th Trophy Achieved 00:07 Neural Networks: Further Knowledge 1 lecture • 1min Further Knowledge is here 00:08 Final Words 1 lecture • 1min Final Words 00:29 Requirements 1. Excel and PowerPoint (Office 2010+) 2. Maths (Basics) 3. A Plus: Calculus and Derivatives (Optional, not required) Description Course Achievements (January 2021): +3,100 Worldwide Students enrolled Trophy Awards for Key Section Achievements! ═════════════════════════════════════════════════════ Some Student Reviews are: "This is an excellent course for people who wish to get an introductory experience in learning about Neural Networks." (December 2020). "This is a very good introduction on how ANN work. It helps build intuition both on the backpropagation and the math behind it." (January 2020). "This course does what it claims to do very well." (October 2019) "Very structured and logical" (July 2018). "Enlightening overview of how neural networks operate mathematically." (March 2018). "I just loved this course. The course is very well taught and is divided in easy-to-digest units." (December 2017). ═════════════════════════════════════════════════════ Hi. Thanks for showing interest in this course! What makes this course special: Step-by-Step Neural Network Learning Process, Master topics like Fundamentals, Objectives, Required Datasets, Weights, Biases, Nodes, Activation functions, Feed-Forward Passes, Predictions, Losses, Gradient Descent, Learning, Backpropagation and more! Plus, personalized feedback and help. You ask, I answer directly! This is your BEST resource for Neural Networks (NN) learning! A must for understanding special concepts and not get lost in computing your own NNs: ✅ First: You'll start the Neural Networks Primer with Fundamentals, Objectives, Data and more: Learn concepts using analogies for maximum learning, so you will be fully covered. Learning how NNs learn will be easy with this Primer under your sleeve! ✅ Second: You'll continue the NN Primer with Learning, Backpropagation and Predictions and more topics In an easy and intuitive way, you will understand how they work, This is fundamental in the NN Learning Process. At the end of this section, you will have mastered the NN Primer! Now, you are ready for the Step-by-Step (in-Motion) sections! ✅ Third: You'll start the in-Motion section with Inputs, Weights, Biases, Activations, Nodes and Feed-Forward Passes: See how they work inside an NN, Step-by-step templates, so you can follow every detail, These files will be dynamic, so you'll understand how NNs work as numbers will be updated on-the-fly and right in front of your eyes. ✅ Forth : You'll continue with the in-Motion section with NN Learning, Backpropagation, Tuning and Prediction: You will understand how NNs learn from the data. This all part of the dynamic templates you get to keep. You'll do several examples along the way for maximum learning. Lastly, you'll see what NNs do to make the best predictions. ✅ Fifth: You'll finish the in-Motion section by doing a complete rundown on everyting you've learned so far: You'll see how all NN inner components work for learning and prediction. Pay close attention at how all parts adjust, making the NN learn in front of your eyes. After this section, you will be fully versed on how NNs learn! ✅ Sixth: I will devote a section for more additional knowledge and resources for continous learning. And then, I will conclude with some Final Words . What are the Requirements ? The only thing you'll need for this course is: Excel and PowerPoint: It is that easy! You will also need to bring your Basic Maths too, If you bring your Calculus (Derivatives) knowledge, that will be a big plus for you (but not required), What are some of the Benefits ? As it is usual in my courses, you will get all files and spreadsheets for all lectures. This way you can replicate everything I do immediately after each lecture. Neural Networks are the new thing today. With it, you can explore and engage Artificial Intelligence, which I recommend you to dive in as it's part of the future. Plus, it's very rewarding and fun too! New content coming in the near future, let me know yout thoughts. Lastly, you can post questions or doubts, and I’ll answer to you personally. I hope you find this course as useful as I have creating it! I’ll see you inside, -M.A. Mauricio M. Who this course is for: Once and For All => Learn and Understand Step-by-Step How Neural Networks work with this course Show more Show less Instructor Mauricio Maroto +10,000 students and growing! 4.4 Instructor Rating 1,428 Reviews 11,088 Students 4 Courses Mauricio Maroto holds a Master degree in Industrial Economics from Carlos III University (Madrid, Spain). With more than 8 years of professional experience, he's always been involved in creating insights for strategic decision making through data analysis. From data query, cleaning and processing, to clustering, regression and classification techniques, Mauricio is passionate about finding patterns and trends in large datasets. Mauricio's other passions are his family, friends, his pets and he loves to play soccer, whether indoors or outdoors. He also goes out for a run on weekends (not lately). He also loves topics such as Economics, Programming and Science. Show more Show less Udemy Business Teach on Udemy Get the app About us Contact us Careers Blog Help and Support Affiliate Impressum Kontakt Terms Privacy policy Cookie settings Sitemap © 2021 Udemy, Inc. window.handleCSSToggleButtonClick = function (event) { var target = event.currentTarget; var cssToggleId = target && target.dataset && target.dataset.cssToggleId; var input = cssToggleId && document.getElementById(cssToggleId); if (input) { if (input.dataset.type === 'checkbox') { input.dataset.checked = input.dataset.checked ? '' : 'checked'; } else { input.dataset.checked = input.dataset.allowToggle && input.dataset.checked ? '' : 'checked'; var radios = document.querySelectorAll('[name="' + input.dataset.name + '"]'); for (var i = 0; i (function(){window['__CF$cv$params']={r:'67783a15ae63e658',m:'84b422edecc6e436e3c051b540bd28e8a413122c-1627749191-1800-AYx94i1oVJqv++aLhz7X3pu/ShuDb+3GFEVrbWvJUWzLu9EA2zgQJb2KJ9rrUYRLlgZ3D45MjUnwwlIb5uxYQMPBcvasT8bf3KgA52Ab8IUBfTwYLQdjg/Rj8T4DNc1VL3TE63Ce+Df50IqFuUNExEnIhu3/aFFAi0je3yKW41HFduE+0ZBibqxE46hnKYX3+U6+EjO5n98hrnwNMkFzlv0=',s:[0x4e312ac39e,0xff1bf5214f],}})();
  4. See how Neural Networks LEARN (graphic and dynamic files), follow all causes and effects! Understand KEY ALGORITHMS in NN's (Gradient Descent, Backpropagation and more) Know Types of Neural Networks, Designs and Advanced Topics Course content 8 sections • 56 lectures • 2h 47m total length Expand all sections Introduction 4 lectures • 2min A foreword and Initial Tips 01:16 How to go through this course 00:32 BONUS COUPON: For any course! 00:04 General Note 00:04 Neural Networks PRIMER: Fundamentals, Objective and Data and more 6 lectures • 33min Fundamental Parts of any NEURAL NETWORK Preview 05:18 Debunking Myths and Thruths Preview 08:15 Our first graphic NEURAL NETWORK 05:07 What is the objective of a NEURAL NETWORK? 04:56 What type of data is good for NEURAL NETWORKS? 03:49 What are Training, Validation and Test datasets? 05:24 Quiz 6 questions Neural Networks PRIMER: Learning, Overfitting and Prediction and more 7 lectures • 26min What's a Feed-Forward Pass (FFP)? 07:42 What are Epochs? 02:54 How good are NEURAL NETWORKS at Prediction? 04:05 Quick Exercise 1 00:10 How do NEURAL NETWORKS Learn? 05:38 What types of NEURAL NETWORKS are out there? 05:18 Quiz 4 questions 1st Trophy Achieved 00:05 Neural Networks IN-MOTION: Inputs, Weights, Biases, Activations and Predictions 12 lectures • 30min Preview 1 Preview 01:05 How do Inputs (x) look like? 02:38 How do Nodes (n) look like? 03:18 How do Weights (w) look like? And how to initialize them 05:17 A Quick Note 1 00:09 How do Biases (b) look like? 01:38 How do Activation functions (f) look like? 03:28 How do Activation functions Derivative (f') look like? 04:11 FFP: from Inputs to Nodes 1 and 2 05:01 FFP: from Nodes 1,2 to Node 3 (Prediction output) 03:28 Quick Exercise 2 00:04 Quiz 6 questions 2nd Trophy Achieved 00:04 Neural Networks IN-MOTION: Losses, Backpropagation, Learning and Tuning 16 lectures • 55min Preview 2 Preview 01:16 What's the Loss associated? 06:32 Quick Exercise 3 00:05 Set an initial Learning Rate 02:20 Gradient Descent and Backpropagation 06:04 Deriving Formulas for Node 3 (Optional) 07:19 Backpropagation: Computing Change at Node 3 03:20 Deriving Formulas for Node 1 (Optional) 05:48 Backpropagation: Computing Change at Node 1 04:24 Deriving Formulas for Node 2 (Optional) 01:54 Backpropagation: Computing Change at Node 2 02:21 3rd Trophy Achieved 00:07 Let the Neural Network Learn 06:12 Compare new Results by Learning 02:32 Let the Neural Network Learn more and Compare 05:03 4th Trophy Achieved 00:07 Quiz 5 questions Neural Networks IN-MOTION: Complete Rundown of NN Learning 9 lectures • 20min The Prediction (Y^) and Loss (L) 06:44 Quick Exercise 4 00:10 The Weights (w) 04:28 Quick Exercise 5 00:12 The Biases (b) 03:02 Quick Exercise 6 00:12 Quick Exercise 7 00:06 Complete NN Rundown 04:57 5th Trophy Achieved 00:07 Neural Networks: Further Knowledge 1 lecture • 1min Further Knowledge is here 00:08 Final Words 1 lecture • 1min Final Words 00:29 Requirements 1. Excel and PowerPoint (Office 2010+) 2. Maths (Basics) 3. A Plus: Calculus and Derivatives (Optional, not required) Description Course Achievements (January 2021): +3,100 Worldwide Students enrolled Trophy Awards for Key Section Achievements! ═════════════════════════════════════════════════════ Some Student Reviews are: "This is an excellent course for people who wish to get an introductory experience in learning about Neural Networks." (December 2020). "This is a very good introduction on how ANN work. It helps build intuition both on the backpropagation and the math behind it." (January 2020). "This course does what it claims to do very well." (October 2019) "Very structured and logical" (July 2018). "Enlightening overview of how neural networks operate mathematically." (March 2018). "I just loved this course. The course is very well taught and is divided in easy-to-digest units." (December 2017). ═════════════════════════════════════════════════════ Hi. Thanks for showing interest in this course! What makes this course special: Step-by-Step Neural Network Learning Process, Master topics like Fundamentals, Objectives, Required Datasets, Weights, Biases, Nodes, Activation functions, Feed-Forward Passes, Predictions, Losses, Gradient Descent, Learning, Backpropagation and more! Plus, personalized feedback and help. You ask, I answer directly! This is your BEST resource for Neural Networks (NN) learning! A must for understanding special concepts and not get lost in computing your own NNs: ✅ First: You'll start the Neural Networks Primer with Fundamentals, Objectives, Data and more: Learn concepts using analogies for maximum learning, so you will be fully covered. Learning how NNs learn will be easy with this Primer under your sleeve! ✅ Second: You'll continue the NN Primer with Learning, Backpropagation and Predictions and more topics In an easy and intuitive way, you will understand how they work, This is fundamental in the NN Learning Process. At the end of this section, you will have mastered the NN Primer! Now, you are ready for the Step-by-Step (in-Motion) sections! ✅ Third: You'll start the in-Motion section with Inputs, Weights, Biases, Activations, Nodes and Feed-Forward Passes: See how they work inside an NN, Step-by-step templates, so you can follow every detail, These files will be dynamic, so you'll understand how NNs work as numbers will be updated on-the-fly and right in front of your eyes. ✅ Forth : You'll continue with the in-Motion section with NN Learning, Backpropagation, Tuning and Prediction: You will understand how NNs learn from the data. This all part of the dynamic templates you get to keep. You'll do several examples along the way for maximum learning. Lastly, you'll see what NNs do to make the best predictions. ✅ Fifth: You'll finish the in-Motion section by doing a complete rundown on everyting you've learned so far: You'll see how all NN inner components work for learning and prediction. Pay close attention at how all parts adjust, making the NN learn in front of your eyes. After this section, you will be fully versed on how NNs learn! ✅ Sixth: I will devote a section for more additional knowledge and resources for continous learning. And then, I will conclude with some Final Words . What are the Requirements ? The only thing you'll need for this course is: Excel and PowerPoint: It is that easy! You will also need to bring your Basic Maths too, If you bring your Calculus (Derivatives) knowledge, that will be a big plus for you (but not required), What are some of the Benefits ? As it is usual in my courses, you will get all files and spreadsheets for all lectures. This way you can replicate everything I do immediately after each lecture. Neural Networks are the new thing today. With it, you can explore and engage Artificial Intelligence, which I recommend you to dive in as it's part of the future. Plus, it's very rewarding and fun too! New content coming in the near future, let me know yout thoughts. Lastly, you can post questions or doubts, and I’ll answer to you personally. I hope you find this course as useful as I have creating it! I’ll see you inside, -M.A. Mauricio M. Who this course is for: Once and For All => Learn and Understand Step-by-Step How Neural Networks work with this course Show more Show less Instructor Mauricio Maroto +10,000 students and growing! 4.4 Instructor Rating 1,428 Reviews 11,088 Students 4 Courses Mauricio Maroto holds a Master degree in Industrial Economics from Carlos III University (Madrid, Spain). With more than 8 years of professional experience, he's always been involved in creating insights for strategic decision making through data analysis. From data query, cleaning and processing, to clustering, regression and classification techniques, Mauricio is passionate about finding patterns and trends in large datasets. Mauricio's other passions are his family, friends, his pets and he loves to play soccer, whether indoors or outdoors. He also goes out for a run on weekends (not lately). He also loves topics such as Economics, Programming and Science. Show more Show less Udemy Business Teach on Udemy Get the app About us Contact us Careers Blog Help and Support Affiliate Impressum Kontakt Terms Privacy policy Cookie settings Sitemap © 2021 Udemy, Inc. window.handleCSSToggleButtonClick = function (event) { var target = event.currentTarget; var cssToggleId = target && target.dataset && target.dataset.cssToggleId; var input = cssToggleId && document.getElementById(cssToggleId); if (input) { if (input.dataset.type === 'checkbox') { input.dataset.checked = input.dataset.checked ? '' : 'checked'; } else { input.dataset.checked = input.dataset.allowToggle && input.dataset.checked ? '' : 'checked'; var radios = document.querySelectorAll('[name="' + input.dataset.name + '"]'); for (var i = 0; i (function(){window['__CF$cv$params']={r:'67783a15ae63e658',m:'84b422edecc6e436e3c051b540bd28e8a413122c-1627749191-1800-AYx94i1oVJqv++aLhz7X3pu/ShuDb+3GFEVrbWvJUWzLu9EA2zgQJb2KJ9rrUYRLlgZ3D45MjUnwwlIb5uxYQMPBcvasT8bf3KgA52Ab8IUBfTwYLQdjg/Rj8T4DNc1VL3TE63Ce+Df50IqFuUNExEnIhu3/aFFAi0je3yKW41HFduE+0ZBibqxE46hnKYX3+U6+EjO5n98hrnwNMkFzlv0=',s:[0x4e312ac39e,0xff1bf5214f],}})();
  5. Understand KEY ALGORITHMS in NN's (Gradient Descent, Backpropagation and more) Know Types of Neural Networks, Designs and Advanced Topics Course content 8 sections • 56 lectures • 2h 47m total length Expand all sections Introduction 4 lectures • 2min A foreword and Initial Tips 01:16 How to go through this course 00:32 BONUS COUPON: For any course! 00:04 General Note 00:04 Neural Networks PRIMER: Fundamentals, Objective and Data and more 6 lectures • 33min Fundamental Parts of any NEURAL NETWORK Preview 05:18 Debunking Myths and Thruths Preview 08:15 Our first graphic NEURAL NETWORK 05:07 What is the objective of a NEURAL NETWORK? 04:56 What type of data is good for NEURAL NETWORKS? 03:49 What are Training, Validation and Test datasets? 05:24 Quiz 6 questions Neural Networks PRIMER: Learning, Overfitting and Prediction and more 7 lectures • 26min What's a Feed-Forward Pass (FFP)? 07:42 What are Epochs? 02:54 How good are NEURAL NETWORKS at Prediction? 04:05 Quick Exercise 1 00:10 How do NEURAL NETWORKS Learn? 05:38 What types of NEURAL NETWORKS are out there? 05:18 Quiz 4 questions 1st Trophy Achieved 00:05 Neural Networks IN-MOTION: Inputs, Weights, Biases, Activations and Predictions 12 lectures • 30min Preview 1 Preview 01:05 How do Inputs (x) look like? 02:38 How do Nodes (n) look like? 03:18 How do Weights (w) look like? And how to initialize them 05:17 A Quick Note 1 00:09 How do Biases (b) look like? 01:38 How do Activation functions (f) look like? 03:28 How do Activation functions Derivative (f') look like? 04:11 FFP: from Inputs to Nodes 1 and 2 05:01 FFP: from Nodes 1,2 to Node 3 (Prediction output) 03:28 Quick Exercise 2 00:04 Quiz 6 questions 2nd Trophy Achieved 00:04 Neural Networks IN-MOTION: Losses, Backpropagation, Learning and Tuning 16 lectures • 55min Preview 2 Preview 01:16 What's the Loss associated? 06:32 Quick Exercise 3 00:05 Set an initial Learning Rate 02:20 Gradient Descent and Backpropagation 06:04 Deriving Formulas for Node 3 (Optional) 07:19 Backpropagation: Computing Change at Node 3 03:20 Deriving Formulas for Node 1 (Optional) 05:48 Backpropagation: Computing Change at Node 1 04:24 Deriving Formulas for Node 2 (Optional) 01:54 Backpropagation: Computing Change at Node 2 02:21 3rd Trophy Achieved 00:07 Let the Neural Network Learn 06:12 Compare new Results by Learning 02:32 Let the Neural Network Learn more and Compare 05:03 4th Trophy Achieved 00:07 Quiz 5 questions Neural Networks IN-MOTION: Complete Rundown of NN Learning 9 lectures • 20min The Prediction (Y^) and Loss (L) 06:44 Quick Exercise 4 00:10 The Weights (w) 04:28 Quick Exercise 5 00:12 The Biases (b) 03:02 Quick Exercise 6 00:12 Quick Exercise 7 00:06 Complete NN Rundown 04:57 5th Trophy Achieved 00:07 Neural Networks: Further Knowledge 1 lecture • 1min Further Knowledge is here 00:08 Final Words 1 lecture • 1min Final Words 00:29 Requirements 1. Excel and PowerPoint (Office 2010+) 2. Maths (Basics) 3. A Plus: Calculus and Derivatives (Optional, not required) Description Course Achievements (January 2021): +3,100 Worldwide Students enrolled Trophy Awards for Key Section Achievements! ═════════════════════════════════════════════════════ Some Student Reviews are: "This is an excellent course for people who wish to get an introductory experience in learning about Neural Networks." (December 2020). "This is a very good introduction on how ANN work. It helps build intuition both on the backpropagation and the math behind it." (January 2020). "This course does what it claims to do very well." (October 2019) "Very structured and logical" (July 2018). "Enlightening overview of how neural networks operate mathematically." (March 2018). "I just loved this course. The course is very well taught and is divided in easy-to-digest units." (December 2017). ═════════════════════════════════════════════════════ Hi. Thanks for showing interest in this course! What makes this course special: Step-by-Step Neural Network Learning Process, Master topics like Fundamentals, Objectives, Required Datasets, Weights, Biases, Nodes, Activation functions, Feed-Forward Passes, Predictions, Losses, Gradient Descent, Learning, Backpropagation and more! Plus, personalized feedback and help. You ask, I answer directly! This is your BEST resource for Neural Networks (NN) learning! A must for understanding special concepts and not get lost in computing your own NNs: ✅ First: You'll start the Neural Networks Primer with Fundamentals, Objectives, Data and more: Learn concepts using analogies for maximum learning, so you will be fully covered. Learning how NNs learn will be easy with this Primer under your sleeve! ✅ Second: You'll continue the NN Primer with Learning, Backpropagation and Predictions and more topics In an easy and intuitive way, you will understand how they work, This is fundamental in the NN Learning Process. At the end of this section, you will have mastered the NN Primer! Now, you are ready for the Step-by-Step (in-Motion) sections! ✅ Third: You'll start the in-Motion section with Inputs, Weights, Biases, Activations, Nodes and Feed-Forward Passes: See how they work inside an NN, Step-by-step templates, so you can follow every detail, These files will be dynamic, so you'll understand how NNs work as numbers will be updated on-the-fly and right in front of your eyes. ✅ Forth : You'll continue with the in-Motion section with NN Learning, Backpropagation, Tuning and Prediction: You will understand how NNs learn from the data. This all part of the dynamic templates you get to keep. You'll do several examples along the way for maximum learning. Lastly, you'll see what NNs do to make the best predictions. ✅ Fifth: You'll finish the in-Motion section by doing a complete rundown on everyting you've learned so far: You'll see how all NN inner components work for learning and prediction. Pay close attention at how all parts adjust, making the NN learn in front of your eyes. After this section, you will be fully versed on how NNs learn! ✅ Sixth: I will devote a section for more additional knowledge and resources for continous learning. And then, I will conclude with some Final Words . What are the Requirements ? The only thing you'll need for this course is: Excel and PowerPoint: It is that easy! You will also need to bring your Basic Maths too, If you bring your Calculus (Derivatives) knowledge, that will be a big plus for you (but not required), What are some of the Benefits ? As it is usual in my courses, you will get all files and spreadsheets for all lectures. This way you can replicate everything I do immediately after each lecture. Neural Networks are the new thing today. With it, you can explore and engage Artificial Intelligence, which I recommend you to dive in as it's part of the future. Plus, it's very rewarding and fun too! New content coming in the near future, let me know yout thoughts. Lastly, you can post questions or doubts, and I’ll answer to you personally. I hope you find this course as useful as I have creating it! I’ll see you inside, -M.A. Mauricio M. Who this course is for: Once and For All => Learn and Understand Step-by-Step How Neural Networks work with this course Show more Show less Instructor Mauricio Maroto +10,000 students and growing! 4.4 Instructor Rating 1,428 Reviews 11,088 Students 4 Courses Mauricio Maroto holds a Master degree in Industrial Economics from Carlos III University (Madrid, Spain). With more than 8 years of professional experience, he's always been involved in creating insights for strategic decision making through data analysis. From data query, cleaning and processing, to clustering, regression and classification techniques, Mauricio is passionate about finding patterns and trends in large datasets. Mauricio's other passions are his family, friends, his pets and he loves to play soccer, whether indoors or outdoors. He also goes out for a run on weekends (not lately). He also loves topics such as Economics, Programming and Science. Show more Show less Udemy Business Teach on Udemy Get the app About us Contact us Careers Blog Help and Support Affiliate Impressum Kontakt Terms Privacy policy Cookie settings Sitemap © 2021 Udemy, Inc. window.handleCSSToggleButtonClick = function (event) { var target = event.currentTarget; var cssToggleId = target && target.dataset && target.dataset.cssToggleId; var input = cssToggleId && document.getElementById(cssToggleId); if (input) { if (input.dataset.type === 'checkbox') { input.dataset.checked = input.dataset.checked ? '' : 'checked'; } else { input.dataset.checked = input.dataset.allowToggle && input.dataset.checked ? '' : 'checked'; var radios = document.querySelectorAll('[name="' + input.dataset.name + '"]'); for (var i = 0; i (function(){window['__CF$cv$params']={r:'67783a15ae63e658',m:'84b422edecc6e436e3c051b540bd28e8a413122c-1627749191-1800-AYx94i1oVJqv++aLhz7X3pu/ShuDb+3GFEVrbWvJUWzLu9EA2zgQJb2KJ9rrUYRLlgZ3D45MjUnwwlIb5uxYQMPBcvasT8bf3KgA52Ab8IUBfTwYLQdjg/Rj8T4DNc1VL3TE63Ce+Df50IqFuUNExEnIhu3/aFFAi0je3yKW41HFduE+0ZBibqxE46hnKYX3+U6+EjO5n98hrnwNMkFzlv0=',s:[0x4e312ac39e,0xff1bf5214f],}})();
  6. Know Types of Neural Networks, Designs and Advanced Topics Course content 8 sections • 56 lectures • 2h 47m total length Expand all sections Introduction 4 lectures • 2min A foreword and Initial Tips 01:16 How to go through this course 00:32 BONUS COUPON: For any course! 00:04 General Note 00:04 Neural Networks PRIMER: Fundamentals, Objective and Data and more 6 lectures • 33min Fundamental Parts of any NEURAL NETWORK Preview 05:18 Debunking Myths and Thruths Preview 08:15 Our first graphic NEURAL NETWORK 05:07 What is the objective of a NEURAL NETWORK? 04:56 What type of data is good for NEURAL NETWORKS? 03:49 What are Training, Validation and Test datasets? 05:24 Quiz 6 questions Neural Networks PRIMER: Learning, Overfitting and Prediction and more 7 lectures • 26min What's a Feed-Forward Pass (FFP)? 07:42 What are Epochs? 02:54 How good are NEURAL NETWORKS at Prediction? 04:05 Quick Exercise 1 00:10 How do NEURAL NETWORKS Learn? 05:38 What types of NEURAL NETWORKS are out there? 05:18 Quiz 4 questions 1st Trophy Achieved 00:05 Neural Networks IN-MOTION: Inputs, Weights, Biases, Activations and Predictions 12 lectures • 30min Preview 1 Preview 01:05 How do Inputs (x) look like? 02:38 How do Nodes (n) look like? 03:18 How do Weights (w) look like? And how to initialize them 05:17 A Quick Note 1 00:09 How do Biases (b) look like? 01:38 How do Activation functions (f) look like? 03:28 How do Activation functions Derivative (f') look like? 04:11 FFP: from Inputs to Nodes 1 and 2 05:01 FFP: from Nodes 1,2 to Node 3 (Prediction output) 03:28 Quick Exercise 2 00:04 Quiz 6 questions 2nd Trophy Achieved 00:04 Neural Networks IN-MOTION: Losses, Backpropagation, Learning and Tuning 16 lectures • 55min Preview 2 Preview 01:16 What's the Loss associated? 06:32 Quick Exercise 3 00:05 Set an initial Learning Rate 02:20 Gradient Descent and Backpropagation 06:04 Deriving Formulas for Node 3 (Optional) 07:19 Backpropagation: Computing Change at Node 3 03:20 Deriving Formulas for Node 1 (Optional) 05:48 Backpropagation: Computing Change at Node 1 04:24 Deriving Formulas for Node 2 (Optional) 01:54 Backpropagation: Computing Change at Node 2 02:21 3rd Trophy Achieved 00:07 Let the Neural Network Learn 06:12 Compare new Results by Learning 02:32 Let the Neural Network Learn more and Compare 05:03 4th Trophy Achieved 00:07 Quiz 5 questions Neural Networks IN-MOTION: Complete Rundown of NN Learning 9 lectures • 20min The Prediction (Y^) and Loss (L) 06:44 Quick Exercise 4 00:10 The Weights (w) 04:28 Quick Exercise 5 00:12 The Biases (b) 03:02 Quick Exercise 6 00:12 Quick Exercise 7 00:06 Complete NN Rundown 04:57 5th Trophy Achieved 00:07 Neural Networks: Further Knowledge 1 lecture • 1min Further Knowledge is here 00:08 Final Words 1 lecture • 1min Final Words 00:29 Requirements 1. Excel and PowerPoint (Office 2010+) 2. Maths (Basics) 3. A Plus: Calculus and Derivatives (Optional, not required) Description Course Achievements (January 2021): +3,100 Worldwide Students enrolled Trophy Awards for Key Section Achievements! ═════════════════════════════════════════════════════ Some Student Reviews are: "This is an excellent course for people who wish to get an introductory experience in learning about Neural Networks." (December 2020). "This is a very good introduction on how ANN work. It helps build intuition both on the backpropagation and the math behind it." (January 2020). "This course does what it claims to do very well." (October 2019) "Very structured and logical" (July 2018). "Enlightening overview of how neural networks operate mathematically." (March 2018). "I just loved this course. The course is very well taught and is divided in easy-to-digest units." (December 2017). ═════════════════════════════════════════════════════ Hi. Thanks for showing interest in this course! What makes this course special: Step-by-Step Neural Network Learning Process, Master topics like Fundamentals, Objectives, Required Datasets, Weights, Biases, Nodes, Activation functions, Feed-Forward Passes, Predictions, Losses, Gradient Descent, Learning, Backpropagation and more! Plus, personalized feedback and help. You ask, I answer directly! This is your BEST resource for Neural Networks (NN) learning! A must for understanding special concepts and not get lost in computing your own NNs: ✅ First: You'll start the Neural Networks Primer with Fundamentals, Objectives, Data and more: Learn concepts using analogies for maximum learning, so you will be fully covered. Learning how NNs learn will be easy with this Primer under your sleeve! ✅ Second: You'll continue the NN Primer with Learning, Backpropagation and Predictions and more topics In an easy and intuitive way, you will understand how they work, This is fundamental in the NN Learning Process. At the end of this section, you will have mastered the NN Primer! Now, you are ready for the Step-by-Step (in-Motion) sections! ✅ Third: You'll start the in-Motion section with Inputs, Weights, Biases, Activations, Nodes and Feed-Forward Passes: See how they work inside an NN, Step-by-step templates, so you can follow every detail, These files will be dynamic, so you'll understand how NNs work as numbers will be updated on-the-fly and right in front of your eyes. ✅ Forth : You'll continue with the in-Motion section with NN Learning, Backpropagation, Tuning and Prediction: You will understand how NNs learn from the data. This all part of the dynamic templates you get to keep. You'll do several examples along the way for maximum learning. Lastly, you'll see what NNs do to make the best predictions. ✅ Fifth: You'll finish the in-Motion section by doing a complete rundown on everyting you've learned so far: You'll see how all NN inner components work for learning and prediction. Pay close attention at how all parts adjust, making the NN learn in front of your eyes. After this section, you will be fully versed on how NNs learn! ✅ Sixth: I will devote a section for more additional knowledge and resources for continous learning. And then, I will conclude with some Final Words . What are the Requirements ? The only thing you'll need for this course is: Excel and PowerPoint: It is that easy! You will also need to bring your Basic Maths too, If you bring your Calculus (Derivatives) knowledge, that will be a big plus for you (but not required), What are some of the Benefits ? As it is usual in my courses, you will get all files and spreadsheets for all lectures. This way you can replicate everything I do immediately after each lecture. Neural Networks are the new thing today. With it, you can explore and engage Artificial Intelligence, which I recommend you to dive in as it's part of the future. Plus, it's very rewarding and fun too! New content coming in the near future, let me know yout thoughts. Lastly, you can post questions or doubts, and I’ll answer to you personally. I hope you find this course as useful as I have creating it! I’ll see you inside, -M.A. Mauricio M. Who this course is for: Once and For All => Learn and Understand Step-by-Step How Neural Networks work with this course Show more Show less Instructor Mauricio Maroto +10,000 students and growing! 4.4 Instructor Rating 1,428 Reviews 11,088 Students 4 Courses Mauricio Maroto holds a Master degree in Industrial Economics from Carlos III University (Madrid, Spain). With more than 8 years of professional experience, he's always been involved in creating insights for strategic decision making through data analysis. From data query, cleaning and processing, to clustering, regression and classification techniques, Mauricio is passionate about finding patterns and trends in large datasets. Mauricio's other passions are his family, friends, his pets and he loves to play soccer, whether indoors or outdoors. He also goes out for a run on weekends (not lately). He also loves topics such as Economics, Programming and Science. Show more Show less Udemy Business Teach on Udemy Get the app About us Contact us Careers Blog Help and Support Affiliate Impressum Kontakt Terms Privacy policy Cookie settings Sitemap © 2021 Udemy, Inc. window.handleCSSToggleButtonClick = function (event) { var target = event.currentTarget; var cssToggleId = target && target.dataset && target.dataset.cssToggleId; var input = cssToggleId && document.getElementById(cssToggleId); if (input) { if (input.dataset.type === 'checkbox') { input.dataset.checked = input.dataset.checked ? '' : 'checked'; } else { input.dataset.checked = input.dataset.allowToggle && input.dataset.checked ? '' : 'checked'; var radios = document.querySelectorAll('[name="' + input.dataset.name + '"]'); for (var i = 0; i (function(){window['__CF$cv$params']={r:'67783a15ae63e658',m:'84b422edecc6e436e3c051b540bd28e8a413122c-1627749191-1800-AYx94i1oVJqv++aLhz7X3pu/ShuDb+3GFEVrbWvJUWzLu9EA2zgQJb2KJ9rrUYRLlgZ3D45MjUnwwlIb5uxYQMPBcvasT8bf3KgA52Ab8IUBfTwYLQdjg/Rj8T4DNc1VL3TE63Ce+Df50IqFuUNExEnIhu3/aFFAi0je3yKW41HFduE+0ZBibqxE46hnKYX3+U6+EjO5n98hrnwNMkFzlv0=',s:[0x4e312ac39e,0xff1bf5214f],}})();