Zou Lan. Meta-Learning: Theory, Algorithms and Applications

Academic Press/Elsevier, 2023. — 404 p. — ISBN: 978-0-323-89931-4.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 solve intelligent tasks that humans can achieve, even transcending what they can achieve. Meta-Learning: Theory, Algorithms, and Applications show how meta-learning with DNNs advances toward AGI. Machine Learning (ML) as a field is “concerned with the question of how to construct computer programs that automatically improve with experience.” A computer program is said to learn from experience E concerning some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E. According to the characteristics of signal and feedback, Machine Learning approaches are commonly categorized into three groups: supervised learning, unsupervised learning, and reinforcement learning.