One-shot learning has been an active field of research for many scientists who are trying to find a cognitive machine that is as close to human beings as possible in terms of learning. As there are various theories as to how humans effect one-shot learning, there are a variety of different methods available to achieve this, ranging from non-parametric models and deep learning architectures to probabilistic models.
Hands-On One-shot Learning with Python will focus on designing and learning about models that can learn information relating to an object from one, or only a few, training examples. The book will begin by giving you a brief overview of deep learning and one-shot learning to get you started. Then, you will learn different methods to achieve this, including non-parametric models, deep learning architectures, and probabilistic models. Once you are well versed in the core principles, you will explore some of the practical real-world examples and implementations of one-shot learning using scikit-learn and PyTorch.
By the end of the book, you will be familiar with one-shot and few-shots learning methods and be able to accelerate your deep learning processes with one-shot learning.