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

On reward and gratification

Interestingly, a group of Stanford researchers showed (Marshmallow experiment, in the 1970s, led by psychologist Walter Mischel) how the capability for individuals to delay short term gratification was correlated with more successful outcomes in the long term. Essentially, these researchers called upon children and observed their behavior once they were presented with a set of choices. The children were given two choices that determined how many total marshmallows they could receive during an interaction. They could either choose to cash out one marshmallow on the spot, or cash out two marshmallows if they chose to wait it out for 15 minutes. This experiment gave keen insight into how interpreting reward signals are beneficial or detrimental for performing in a given environment as the subjects who chose two marshmallows turned out to be more successful...