Book Image

Hands-On Neural Networks with Keras

By : Niloy Purkait
Book Image

Hands-On Neural Networks with Keras

By: Niloy Purkait

Overview of this book

Neural networks are used to solve a wide range of problems in different areas of AI and deep learning. Hands-On Neural Networks with Keras will start with teaching you about the core concepts of neural networks. You will delve into combining different neural network models and work with real-world use cases, including computer vision, natural language understanding, synthetic data generation, and many more. Moving on, you will become well versed with convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short-term memory (LSTM) networks, autoencoders, and generative adversarial networks (GANs) using real-world training datasets. We will examine how to use CNNs for image recognition, how to use reinforcement learning agents, and many more. We will dive into the specific architectures of various networks and then implement each of them in a hands-on manner using industry-grade frameworks. By the end of this book, you will be highly familiar with all prominent deep learning models and frameworks, and the options you have when applying deep learning to real-world scenarios and embedding artificial intelligence as the core fabric of your organization.
Table of Contents (16 chapters)
Free Chapter
1
Section 1: Fundamentals of Neural Networks
5
Section 2: Advanced Neural Network Architectures
10
Section 3: Hybrid Model Architecture
13
Section 4: Road Ahead

Vectorizing labels

We can also vectorize our training labels, which simply helps our network handle our data better. You can think of vectorization as an efficient way to represent information to computers. Just like humans are not very good at performing computations using Roman numerals, computers are notoriously worse off when dealing with unvectorized data. In the following code, we are transforming our labels into NumPy arrays that contain 32-bit floating-point arithmetic values of either 0.0 or 1.0:

y_train= np.asarray(y_train).astype('float32')
y_test = np.asarray(y_test).astype('float32')

Finally, we have our tensor, ready to be consumed by a neural network. This 2D tensor is essentially 25,000 stacked vectors, each with its own label. All that is left to do is build our network.