Book Image

Deep Learning with PyTorch

By : Vishnu Subramanian
Book Image

Deep Learning with PyTorch

By: Vishnu Subramanian

Overview of this book

Deep learning powers the most intelligent systems in the world, such as Google Voice, Siri, and Alexa. Advancements in powerful hardware, such as GPUs, software frameworks such as PyTorch, Keras, TensorFlow, and CNTK along with the availability of big data have made it easier to implement solutions to problems in the areas of text, vision, and advanced analytics. This book will get you up and running with one of the most cutting-edge deep learning libraries—PyTorch. PyTorch is grabbing the attention of deep learning researchers and data science professionals due to its accessibility, efficiency and being more native to Python way of development. You'll start off by installing PyTorch, then quickly move on to learn various fundamental blocks that power modern deep learning. You will also learn how to use CNN, RNN, LSTM and other networks to solve real-world problems. This book explains the concepts of various state-of-the-art deep learning architectures, such as ResNet, DenseNet, Inception, and Seq2Seq, without diving deep into the math behind them. You will also learn about GPU computing during the course of the book. You will see how to train a model with PyTorch and dive into complex neural networks such as generative networks for producing text and images. By the end of the book, you'll be able to implement deep learning applications in PyTorch with ease.
Table of Contents (11 chapters)

Recursive neural networks

RNNs are among the most powerful models that enable us to take on applications such as classification, labeling on sequential data, generating sequences of text (such as with the SwiftKey Keyboard app which predicts the next word), and converting one sequence to another such as translating a language, say, from French to English. Most of the model architectures such as feedforward neural networks do not take advantage of the sequential nature of data. For example, we need the data to present the features of each example in a vector, say all the tokens that represent a sentence, paragraph, or documents. Feedforward networks are designed just to look at all the features once and map them to output. Let's look at a text example which shows why the order, or sequential nature, is important of text. I had cleaned my car and I had my car cleaned are two...