by Beau Carnes | Released May 2019 | ISBN: 10000MNLV201802

Beau Carnes does it again; Breaking down one of the most complex fields of computer science and distilling it into repeatable, practical lessons to enhance a developer's skillset. Derek Hampton Despite being one of the biggest technical leaps in AI in decades, building an understanding in deep learning doesn't mean you need a math degree. All it takes is the right intuitive approach, and you'll be writing your own neural networks in pure Python in no time! Grokking Deep Learning in Motion is a new course that takes you on a journey into the world of deep learning. Rather than just learn how to use a single library or framework, you'll actually discover how to build these algorithms completely from scratch! Professional instructor Beau Carnes breaks deep learning wide open, drawing together his expertise in video instruction and Andrew Trask's unique, intuitive approach from Grokking Deep Learning! As you move through this course, you'll learn the fundamentals of deep learning from a unique standing! Using Python, as well as Jupyter Notebooks, you'll get stuck right in to the basics of neural prediction and learning, and teach your algorithms to visualize things like different weights. Throughout, you'll train your neural network to be smarter, faster, and better at its job in a variety of ways, ready for the real world! Packed with great animations and explanations that bring the world of deep learning to life in a way that just makes sense, Grokking Deep Learning in Motion is exactly what anyone needs to build an intuitive understanding of one of the hottest techniques in machine learning. This course also works perfectly alongside the original book Grokking Deep Learning by Andrew Trask, bringing his unique way to teaching to life. Machine learning has made remarkable progress in recent years. Deep-learning systems now enable previously impossible smart applications, revolutionizing image recognition and natural-language processing, and identifying complex patterns in data. To really get the most out of deep learning, you need to understand it inside and out, but where do you start? This course is the perfect jumping off point! Inside: The differences between deep and machine learning An introduction to neural prediction Building your first deep neural network The importance of visualization tools Memorization vs Generalization Modeling probabilities and non-linearities This course is perfect for anyone with high school-level math and basic programming skills with a language like Python. Experience with Calculus is helpful but NOT required. Beau Carnes is a software developer and a recognized authority in software instruction. Besides teaching in-person workshops and classes, Beau has recently joined the team at freeCodeCamp as their lead video instructor, helping to teach over 2 million people around the world to code. Beau also teaches Manning's best-selling video course, Algorithms in Motion. Excellent bottom-up introduction to neural networks and deep learning. Ursin Stauss Using small snippets of easily memorized code introduced through the various chapters, the video shows a relatively easy way of building a deep learning neural network. Thomas Heiman Beau's approach is refreshingly beautiful. Markus Breuer Show and hide more

1. INTRODUCING DEEP LEARNING
   • Introduction 00:08:54
   • What you need to get started 00:05:28
2. FUNDAMENTAL CONCEPTS
   • What is Deep Learning and Machine Learning? 00:05:02
   • Supervised vs. unsupervised learning 00:05:23
   • Parametric vs. non-parametric learning 00:12:56
3. INTRODUCTION TO NEURAL PREDICTION
   • Making a prediction 00:07:56
   • What does a Neural Network do? 00:04:05
   • Multiple inputs 00:13:25
   • Multiple outputs and stacking predictions 00:09:15
   • Primer on NumPy 00:11:27
4. INTRODUCTION TO NEURAL LEARNING
   • Compare and learn 00:06:23
   • Why measure error? 00:03:53
   • Hot and cold learning 00:09:17
   • Gradient descent 00:09:21
   • Learning with gradient decent 00:09:06
   • The secret to learning 00:07:13
   • How to use a derivative to learn 00:11:41
   • Alpha 00:06:13
5. LEARNING MULTIPLE WEIGHTS AT A TIME
   • Gradient descent learning with multiple inputs 00:07:16
   • Several steps of learning 00:06:04
   • Gradient descent with multiple outputs 00:06:17
   • Visualizing weight values 00:09:32
6. BUILDING YOUR FIRST "DEEP" NEURAL NETWORK
   • The streetlight problem 00:10:32
   • Building our neural network 00:09:37
   • Up and down pressure 00:14:41
   • Correlation and backpropagation 00:08:04
   • Linear vs. non-linear 00:08:06
   • Our first "deep" neural network 00:10:14
7. HOW TO PICTURE NEURAL NETWORKS
   • Simplifying 00:06:35
   • Simplified visualization 00:07:16
   • Seeing the network predict 00:08:04
8. LEARNING SIGNAL AND IGNORING NOISE
   • 3-layer network on MNIST 00:10:59
   • Overfitting in Neural Networks 00:06:06
   • Regularization: Early Stopping and Dropout 00:16:45
9. MODELING PROBABILITIES AND NON-LINEARITIES
   • Activation Function Constraints 00:09:31
   • Standard Activation Functions 00:12:22
   • Softmax and implementation in code 00:16:35
10. CONCLUSION
    • Where to go from here 00:07:17
Show and hide more