Hands-On Deep Learning with Go

By : Seneque, Chua

3 (2)

Buy this Book

Hands-On Deep Learning with Go

3 (2)

By: Seneque, Chua

Buy this Book

Overview of this book

Go is an open source programming language designed by Google for handling large-scale projects efficiently. The Go ecosystem comprises some really powerful deep learning tools such as DQN and CUDA. With this book, you'll be able to use these tools to train and deploy scalable deep learning models from scratch. This deep learning book begins by introducing you to a variety of tools and libraries available in Go. It then takes you through building neural networks, including activation functions and the learning algorithms that make neural networks tick. In addition to this, you'll learn how to build advanced architectures such as autoencoders, restricted Boltzmann machines (RBMs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), and more. You'll also understand how you can scale model deployments on the AWS cloud infrastructure for training and inference. By the end of this book, you'll have mastered the art of building, training, and deploying deep learning models in Go to solve real-world problems.

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

Section 1: Deep Learning in Go, Neural Networks, and How to Train Them

Introduction to Deep Learning in Go

Introducing DL

Overview of ML in Go

Using Gorgonia

Summary

What Is a Neural Network and How Do I Train One?

A basic neural network

Activation functions

Gradient descent and backpropagation

Advanced gradient descent algorithms

Summary

Beyond Basic Neural Networks - Autoencoders and RBMs

Loading data – MNIST

Building a neural network for handwriting recognition

Building an autoencoder – generating MNIST digits

Building an RBM for Netflix-style collaborative filtering

Summary

Further reading

CUDA - GPU-Accelerated Training

CPUs versus GPUs

Understanding Gorgonia and CUDA

Building a model in Gorgonia with CUDA support

Performance benchmarking of CPU versus GPU models for training and inference

Summary

Section 2: Implementing Deep Neural Network Architectures

Next Word Prediction with Recurrent Neural Networks

Vanilla RNNs

Training RNNs

RNNs and vanishing gradients

Augmenting your RNN with GRU/LSTM units

Building an LSTM in Gorgonia

Summary

Object Recognition with Convolutional Neural Networks

Introduction to CNNs

Building an example CNN

Assessing the results

Summary

Further reading

Maze Solving with Deep Q-Networks

What is a DQN?

Solving a maze using a DQN in Gorgonia

Summary

Further reading

Generative Models with Variational Autoencoders

Introduction to VAEs

Building a VAE on MNIST

Assessing the results

Summary

Further reading

Section 3: Pipeline, Deployment, and Beyond!

Building a Deep Learning Pipeline

Exploring Pachyderm

Integrating our CNN

Summary

Scaling Deployment

Lost (and found) in the cloud

Building deployment templates

Running a model on a K8s cluster

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

3 (2)

5 star

50%

4 star

3 star

2 star

1 star

50%

Vanilla RNNs

According to their more utopian description, RNNs are able to do something that the networks we've covered so far cannot: remember. More precisely, in a simple network with a single hidden layer, the network's output, as well as the state of that hidden layer, are combined with the next element in a training sequence to form the input for a new network (with its own trainable, hidden state). A vanilla RNN can be visualized as follows:

Let's unpack this a bit. The two networks in the preceding diagram are two different representations of the same thing. One is in a Rolled state, which is simply an abstract representation of the computation graph, where an infinite number of timesteps is represented by (t). We then use the Unrolled RNN as we feed the network data and train it.

For a given forward pass, this network takes two inputs, where X is a representation...