by Anand Saha | Released April 2018 | ISBN: 9781788475266

Build useful and effective deep learning models with the PyTorch Deep Learning frameworkAbout This VideoExplore PyTorch and the impact it has made on Deep LearningDesign and implement powerful neural networks to solve some impressive problems in a step-by-step mannerFollow the examples to solve similar use cases outside this courseIn DetailThis video course will get you up-and-running with one of the most cutting-edge deep learning libraries: PyTorch. Written in Python, PyTorch is grabbing the attention of all data science professionals due to its ease of use over other libraries and its use of dynamic computation graphs.In this course, you will learn how to accomplish useful tasks using Convolutional Neural Networks to process spatial data such as images and using Recurrent Neural Networks to process sequential data such as texts. You will explore how you can make use of unlabeled data using Auto Encoders. You will also be training a neural network to learn how to balance a pole all by itself, using Reinforcement Learning. Throughout this journey, you will implement various mechanisms of the PyTorch framework to do these tasks.By the end of the video course, you will have developed a good understanding of, and feeling for, the algorithms and techniques used. You'll have a good knowledge of how PyTorch works and how you can use it in to solve your daily machine learning problems. Show and hide more Publisher Resources Download Example Code

1. Chapter 1 : Getting Started With PyTorch
   • The Course Overview 00:06:29
   • Introduction to PyTorch 00:06:18
   • Installing PyTorch on Linux and Windows 00:10:41
   • Installing CUDA 00:04:41
   • Introduction to Tensors and Variables 00:16:17
   • Working with PyTorch and NumPy 00:02:38
   • Working with PyTorch and GPU 00:03:07
   • Handling Datasets in PyTorch 00:08:30
   • Deep Learning Using PyTorch 00:08:18
2. Chapter 2 : Training Your First Neural Network
   • Building a Simple Neural Network 00:13:27
   • Loss Functions in PyTorch 00:02:07
   • Optimizers in PyTorch 00:03:50
   • Training the Neural Network 00:06:36
   • Saving and Loading a Trained Neural Network 00:01:28
   • Training the Neural Network on a GPU 00:03:47
3. Chapter 3 : Computer Vision – CNN for Digits Recognition
   • Computer Vision Motivation 00:04:57
   • Convolutional Neural Networks 00:08:09
   • The Convolution Operation 00:09:28
   • Concepts - Strides, Padding, and Pooling 00:09:28
   • Loading and Using MNIST Dataset 00:09:06
   • Building the Model 00:08:57
   • Training and Testing 00:11:54
4. Chapter 4 : Sequence Models – RNN for Text Generation
   • Sequence Models Motivation 00:04:55
   • Word Embedding 00:06:46
   • Recurrent Neural Networks 00:10:45
   • Building a Text Generation Model in PyTorch 00:17:26
   • Training and Testing 00:07:27
5. Chapter 5 : Autoencoder - Denoising Images
   • Autoencoders Motivation 00:04:32
   • How Autoencoders Work 00:03:21
   • Types of Autoencoders 00:03:58
   • Building Denoising Autoencoder Using PyTorch 00:11:23
   • Training and Testing 00:04:18
6. Chapter 6 : Reinforcement Learning – Balance Cartpole Using DQN
   • Reinforcement Learning Motivation 00:06:11
   • Reinforcement Learning Concepts 00:10:55
   • DQN, Experience Replay 00:06:07
   • The OpenAI Gym Environment 00:06:11
   • Building the Cartpole Agent Using DQN 00:08:27
   • Training and Testing 00:09:51
Show and hide more