Book Image

The Deep Learning Workshop

By : Mirza Rahim Baig, Thomas V. Joseph, Nipun Sadvilkar, Mohan Kumar Silaparasetty, Anthony So
Book Image

The Deep Learning Workshop

By: Mirza Rahim Baig, Thomas V. Joseph, Nipun Sadvilkar, Mohan Kumar Silaparasetty, Anthony So

Overview of this book

Are you fascinated by how deep learning powers intelligent applications such as self-driving cars, virtual assistants, facial recognition devices, and chatbots to process data and solve complex problems? Whether you are familiar with machine learning or are new to this domain, The Deep Learning Workshop will make it easy for you to understand deep learning with the help of interesting examples and exercises throughout. The book starts by highlighting the relationship between deep learning, machine learning, and artificial intelligence and helps you get comfortable with the TensorFlow 2.0 programming structure using hands-on exercises. You’ll understand neural networks, the structure of a perceptron, and how to use TensorFlow to create and train models. The book will then let you explore the fundamentals of computer vision by performing image recognition exercises with convolutional neural networks (CNNs) using Keras. As you advance, you’ll be able to make your model more powerful by implementing text embedding and sequencing the data using popular deep learning solutions. Finally, you’ll get to grips with bidirectional recurrent neural networks (RNNs) and build generative adversarial networks (GANs) for image synthesis. By the end of this deep learning book, you’ll have learned the skills essential for building deep learning models with TensorFlow and Keras.
Table of Contents (9 chapters)
Preface

More Variants of RNNs

We've seen quite a few variations of RNNs in this chapter – covering all the prominent ones and the major upcoming (in terms of popularity) variations. Sequence modeling and its associated architectures are a hot area of research, and we see plenty of developments coming in every year. Many variants aim to make lighter models with fewer parameters that aren't as hardware hungry as current RNNs. Clockwork RNNs (CWRNNs) are a recent development and show great success. There are also Hierarchal Attention Networks, built on the idea of attention, but ultimately also propose that you shouldn't use RNNs as building blocks. There's a lot going on in this exciting area, so keep your eyes and ears open for the next big idea.

Activity 6.01: Sentiment Analysis of Amazon Product Reviews

So far, we've looked at the variants of RNNs and used them to predict sentiment on movie reviews from the IMDb dataset. In this activity, we will build...