Meta-Learning: An Overview explains the fundamentals of meta-learning, providing an understanding of the concept of learning to learn. After giving a background to artificial intelligence, machine learning, deep learning, deep reinforcement learning, and meta-learning, the book provides important state-of-the-art mechanisms 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 Reptile. The book then demonstrates the application of the principles and algorithms of meta learning in computer vision, meta-reinforcement learning, robotics, speech recognition, natural language processing, finance, business management and health care. A final chapter summarizes future trends. Users, including students and researchers will find updates on the principles and state-of-the-art meta-learning algorithms, thus enabling the use of meta-learning for a range of applications. Provides a comprehensive overview of the state-of-the-art in meta-learning techniques Presents the three approaches to meta-learning: model-based, metric-based and optimization-based Gives strategies of meta-learning in multiple subfields of machine learning and AI that focus on developing versatile systems, including unsupervised learning, Bayesian inference, multi-task learning, transfer learning and lifelong learning Presents applications in computer vision, meta-reinforcement learning, robotics, speech recognition, natural language processing, finance and business management INDICE: 1. Background: Machine Learning, Bayesian Inference, Deep Learning, Reinforcement Learning, Meta-learning, One-Shot Learning, and Algorithm Part I: Approach and Mechanisms 2. Model-Based Meta-learning Algorithms: Memory - Augmented Neural Networks and Meta Networks 3. Metric-Based Meta-learning Algorithms: Convolutional Siamese Neural Networks, Matching Networks, Prototypical Networks, and Relation Networks 4. Optimization-Based Meta-learning Algorithms: LSTM Meta-learner, Model-agnostic Meta-learning, and Reptile 5. Others: Unsupervised Meta-learning, Bayesian Meta-learning, Multi-task/Transfer Meta-learning, Lifelong Learning, and AutoML Part II: Application - Next, the book introduces a wide range of meta-learning applications in diverse industries and discusses future trends in implementing meta-learning techniques throughout engineering, science, and art 6. Computer Vision 7. Meta Reinforcement Learning 8. Robotics 9. Speech Recognition and Natural Language Processing 10. Finance and business management 11. More applications: Healthcare, transportation, music, chemistry, and physics
- ISBN: 978-0-323-89931-4
- Editorial: Academic Press
- Encuadernacion: Rústica
- Páginas: 225
- Fecha Publicación: 01/10/2022
- Nº Volúmenes: 1
- Idioma: Inglés