Book Image

Hands-On Transfer Learning with Python

By : Dipanjan Sarkar, Raghav Bali, Tamoghna Ghosh
Book Image

Hands-On Transfer Learning with Python

By: Dipanjan Sarkar, Raghav Bali, Tamoghna Ghosh

Overview of this book

Transfer learning is a machine learning (ML) technique where knowledge gained during training a set of problems can be used to solve other similar problems. The purpose of this book is two-fold; firstly, we focus on detailed coverage of deep learning (DL) and transfer learning, comparing and contrasting the two with easy-to-follow concepts and examples. The second area of focus is real-world examples and research problems using TensorFlow, Keras, and the Python ecosystem with hands-on examples. The book starts with the key essential concepts of ML and DL, followed by depiction and coverage of important DL architectures such as convolutional neural networks (CNNs), deep neural networks (DNNs), recurrent neural networks (RNNs), long short-term memory (LSTM), and capsule networks. Our focus then shifts to transfer learning concepts, such as model freezing, fine-tuning, pre-trained models including VGG, inception, ResNet, and how these systems perform better than DL models with practical examples. In the concluding chapters, we will focus on a multitude of real-world case studies and problems associated with areas such as computer vision, audio analysis and natural language processing (NLP). By the end of this book, you will be able to implement both DL and transfer learning principles in your own systems.
Table of Contents (14 chapters)

Introduction

Before we dive in detail of neural DeepDream, let's take a glance at a similar behavior we humans experience ourselves. Have you ever tried to look for shapes in clouds, the jitter and noisy signals in your television set or even seen a face burned into your toast?

Pareidolia is a psychological phenomenon that leads us to see patterns in a random stimulus; the tendency for humans to perceive a face or pattern where one actually doesn't exist. This often results in assigning human characteristics to objects. Please note the significance of the evolutionary consequences of seeing a pattern where there is none (a false positive) as opposed to failing to see a pattern where there is one (a false negative). For example, seeing a lion where this is no lion is rarely lethal; however, failing to see a predatory lion where there is one, of course, would often be...