Hands-On One-shot Learning with Python: A practical guide to implementing fast and accurate deep learning models with fewer training samples

English | 2020 | ISBN: 978-1838825461 | 207 Pages | PDF, EPUB, MOBI | 70 MB

Get to grips with building powerful deep learning models using scikit-learn and Keras
One-shot learning has been an active field of research for scientists trying to develop a cognitive machine that mimics human learning. As there are numerous theories about how humans perform one-shot learning, there are several methods to achieve it too.
Hands-On One-Shot Learning with Python will guide you through exploring and designing deep learning models that can grasp information about an object from one or only a few training examples. The book begins with an overview of deep learning and one-shot learning and then introduces you to the different methods you can use to achieve it, such as deep learning architectures and probabilistic models. Once you are well versed with the core principles, you’ll explore some real-world examples and implementations of one-shot learning using scikit-learn and Keras 2.x in computer vision (CV), and natural language processing (NLP).
By the end of this book, you’ll be well-versed with the different one-and few-shot learning methods and be able to build your own deep learning models using them.
What you will learn

• Understand the fundamental concepts of one-and few-shot learning
• Work with different deep learning architectures for one-shot learning
• Understand when to use one-shot and transfer learning respectively
• Study the Bayesian network approach for one-shot learning
• Implement Siamese neural networks and memory-augmented networks in Keras
• Discover different forms of optimization algorithms that help to improve accuracy even with smaller volumes of data
• Explore various computer vision and NLP-based one-shot learning architectures