Purchase textbook

Meta-Learning,

Edition 1 Theory, Algorithms and Applications

Editors: By Lan Zou

Publication Date: 08 Nov 2022

0 Reviews

Conformance

PDF/UA-1
The publication was certified on 20250728
For queries regarding accessibility information, contact [email protected]

Ways Of Reading

This e-publication is accessible to the full extent that the file format and types of content allow, on a specific reading device, by default, without necessarily including any additions such as textual descriptions of images or enhanced navigation.

Navigation

The contents of the PDF have been tagged to permit access by assistive technologies as per PDF-UA-1 standard.
Page breaks included from the original print source

Additional Accessibility Information

The language of the text has been specified (e.g., via the HTML or XML lang attribute) to optimise text-to-speech (and other alternative renderings), both at the whole document level and, where appropriate, for individual words, phrases or passages in a different language.

Note

This product relies on 3rd party tooling which may impact the accessibility features visible in inspection copies. All accessibility features mentioned would be present in the purchased version of the title.

Deep neural networks (DNNs) with their dense and complex algorithms provide real possibilities for Artificial General Intelligence (AGI). Meta-learning with DNNs brings AGI much closer: artificial agents solving intelligent tasks that human beings can achieve, even transcending what they can achieve. Meta-Learning: Theory, Algorithms and Applications shows how meta-learning in combination with DNNs advances towards AGI.

Meta-Learning: Theory, Algorithms and Applications explains the fundamentals of meta-learning by providing answers to these questions: What is meta-learning?; why do we need meta-learning?; how are self-improved meta-learning mechanisms heading for AGI ?; how can we use meta-learning in our approach to specific scenarios? The book presents the background of seven mainstream paradigms: meta-learning, few-shot learning, deep learning, transfer learning, machine learning, probabilistic modeling, and Bayesian inference. It then explains important state-of-the-art mechanisms and their variants for meta-learning, including memory-augmented neural networks, meta-networks, convolutional Siamese neural networks, matching networks, prototypical networks, relation networks, LSTM meta-learning, model-agnostic meta-learning, and the Reptile algorithm.

The book takes a deep dive into nearly 200 state-of-the-art meta-learning algorithms from top tier conferences (e.g. NeurIPS, ICML, CVPR, ACL, ICLR, KDD). It systematically investigates 39 categories of tasks from 11 real-world application fields: Computer Vision, Natural Language Processing, Meta-Reinforcement Learning, Healthcare, Finance and Economy, Construction Materials, Graphic Neural Networks, Program Synthesis, Smart City, Recommended Systems, and Climate Science. Each application field concludes by looking at future trends or by giving a summary of available resources.

Meta-Learning: Theory, Algorithms and Applications is a great resource to understand the principles of meta-learning and to learn state-of-the-art meta-learning algorithms, giving the student, researcher and industry professional the ability to apply meta-learning for various novel applications.

Key Features

A comprehensive overview of state-of-the-art meta-learning techniques and methods associated with deep neural networks together with a broad range of application areas
Coverage of nearly 200 state-of-the-art meta-learning algorithms, which are promoted by premier global AI conferences and journals, and 300 to 450 pieces of key research
Systematic and detailed exploration of the most crucial state-of-the-art meta-learning algorithm mechanisms: model-based, metric-based, and optimization-based
Provides solutions to the limitations of using deep learning and/or machine learning methods, particularly with small sample sizes and unlabeled data
Gives an understanding of how meta-learning acts as a stepping stone to Artificial General Intelligence in 39 categories of tasks from 11 real-world application fields

About the author

By Lan Zou, Columnist, Association for the Advancement of Artificial Intelligence (https://aihub.org/) Researcher, AI, Silicon Valley and Carnegie Mellon University

1. Meta-Learning Basics and Background
2. Model-Based Meta-Learning Approaches
3. Metric-Based Meta-Learning Approaches
4. Optimization-Based Meta-Learning Approaches
5. Meta-Learning for Computer Vision
6. Meta-Learning for Natural Language Processing
7. Meta-Reinforcement Learning
8. Meta-Learning for Health Care
9. Meta-Learning for Emerging Applications: Finance, Building Material, Graph Neural Networks, Program Synthesis, Transportation, Recommendation Systems and Climate Science

ISBN: 9780323899314

Page Count: 402

Retail Price :

9780128104088

Scholars, researchers, engineers, or students interested in high-technology, computer science, statistics, mathematics, artificial intelligence, machine learning, deep learning, self-driven vehicles, automatic systems, computer vision, natural language processing, health care, and robotics.