Meta-Learning: Theory, Algorithms and Applications

Surpassing contemporary machine learning and data mining, deep neural networks (DNNs) as heavy algorithm-based technologies provide solid 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 explains the fundamentals of meta-learning by providing answers to these questions: What is meta-learning?; why do we need meta-learning?; 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. The book concludes with an epilogue looking at future trends.

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

超越當代機器學習和數據挖掘，基於重型算法的深度神經網絡（DNN）為人工通用智能（AGI）提供了堅實的可能性。使用DNN的元學習使AGI更加接近：人工智能代理能夠解決人類可以實現的智能任務，甚至超越其能力。

《元學習：理論、算法和應用》通過回答以下問題來解釋元學習的基礎知識：什麼是元學習？為什麼我們需要元學習？我們如何在特定場景中應用元學習？該書介紹了七種主流範式的背景知識：元學習、少樣本學習、深度學習、遷移學習、機器學習、概率建模和貝葉斯推理。然後，它解釋了元學習的重要最新機制及其變體，包括記憶增強神經網絡、元網絡、卷積孿生神經網絡、匹配網絡、原型網絡、關係網絡、LSTM元學習、模型無關元學習和Reptile算法。

該書深入研究了近200種頂級會議（如NeurIPS、ICML、CVPR、ACL、ICLR、KDD）的最新元學習算法，並系統地調查了11個現實應用領域的39個任務類別：計算機視覺、自然語言處理、元強化學習、醫療保健、金融和經濟、建築材料、圖形神經網絡、程序合成、智慧城市、推薦系統和氣候科學。該書以一個結語展望未來趨勢。

《元學習：理論、算法和應用》是理解元學習原則和學習最新元學習算法的重要資源，使學生、研究人員和行業專業人士能夠將元學習應用於各種新應用領域。