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

Summarizing All the Models

In this chapter, we've looked at different variants of RNNs – from plain RNNs to LSTMs to GRUs. We also looked at the bidirectional approach and the stacking approach to using RNNs. Now is a good time to take a holistic look at things and make a comparison between the models. Let's look at the following table, which compares the five models in terms of parameters, training time, and performance (that is, the level of accuracy on our dataset):

Figure 6.23: Comparing the five models

Note

As mentioned earlier in the chapter, while working through the practical elements, you may have obtained values different from the ones shown above; however, the test accuracies you obtain should largely agree with ours. If the model's performance is very different, you may want to tweak the number of epochs.

Plain RNNs are the lowest on parameters and have the lowest training times but have the lowest accuracy of all the...