▶What You Will Learn
- Get to grips with 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 one-shot learning approaches based on metrics, models, and optimization in PyTorch
- Discover different optimization algorithms that help to improve accuracy even with smaller volumes of data
- Explore various one-shot learning architectures based on classification and regression
▶Key Features
- Learn how you can speed up the deep learning process with one-shot learning
- Use Python and PyTorch to build state-of-the-art one-shot learning models
- Explore architectures such as Siamese networks, memory-augmented neural networks, model-agnostic meta-learning, and discriminative k-shot learning
▶Who This Book Is For
If you're an AI researcher or a machine learning or deep learning expert looking to explore one-shot learning, this book is for you. It will help you get started with implementing various one-shot techniques to train models faster. Some Python programming experience is necessary to understand the concepts covered in this book.
▶What this book covers
- Chapter 1, Introduction to One-shot Learning, tells us what one-shot learning is and how it works. It also tells us about the human brain's workings and how it translates to machine
learning.
- Chapter 2, Metrics-Based Methods, explores methods that use different forms of embeddings, and evaluation metrics, by keeping the core as basic k-nearest neighbors.
- Chapter 3, Model-Based Methods, explores two architectures whose internal architectures help to train a k-shot learning model.
- Chapter 4, Optimization-Based Methods, explores different forms of optimization algorithms, which help in improving accuracy even when the volume of data is low.
- Chapter 5, Generative Modeling-Based Methods, explores the development of a Bayesian learning framework based on representing object categories with probabilistic models.
- Chapter 6, Conclusions and Other Approaches, goes through certain aspects of architecture, metrics, and algorithms to understand how we can determine whether an approach is close to human brain capability.
