Book Image

Hands-On Transfer Learning with Python

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

Hands-On Transfer Learning with Python

By: Dipanjan Sarkar, Nitin Panwar, 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)

Text categorization

Given a set of text documents and a set of predefined categories, the objective of text categorization is to assign each document to a category. The output can be a soft assignment or a hard assignment, depending on the problem. Soft assignment means that the category assignment is defined as a probability distribution over all categories.

There are a wide range of applications of text categorization in industry. The following are a few examples:

  • Spam filtering: Given an email, classify it as spam or legitimate email.
  • Sentiment classification: Given a review text (movie review, product review), identify the user polarity—whether its a positive or negative or neural review.
  • Problem ticket assignment: Typically, in any industry, whenever a user faces an issue regarding any IT application or a software/hardware product, the fist step is to create a problem...