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)

Recurrent Neural Networks

How does our brain process a sentence? Let's try to understand how our brain processes a sentence as we read it. You see some terms in a sentence, and you need to identify the sentiment contained in the sentence (positive, negative, neutral). Let's look at the first term – "I":

Figure 5.8 Sentiment analysis for the first term

"I" is neutral, so our classification (neutral) is appropriate. Let's look at another term:

Figure 5.9: Sentiment analysis with two terms

With the term "can't," we need to update our assessment of the sentiment. "I" and "can't" together typically have a negative connotation, so our current assessment is updated as "negative" and is marked with a cross. Let's look at the next couple of words:

Figure 5.10: Sentiment analysis with four terms

After the...