Hands-On Meta Learning with Python: Meta learning using one-shot learning, MAML, Reptile, and Meta-SGD with TensorFlow

by Sudharsan Ravichandiran

Explore a diverse set of meta-learning algorithms and techniques to enable human-like cognition for your machine learning models using various Python frameworks Meta learning is an exciting research trend in machine learning, which enables a model to understand the learning process. Unlike other ML paradigms, with meta learning you can learn from small datasets faster. Hands-On Meta Learning with Python starts by explaining the fundamentals of meta learning and helps you understand the concept of learning to learn. You will delve into various one-shot learning algorithms, like siamese, prototypical, relation and memory-augmented networks by implementing them in TensorFlow and Keras. As you make your way through the book, you will dive into state-of-the-art meta learning algorithms such as MAML, Reptile, and CAML. You will then explore how to learn quickly with Meta-SGD and discover how you can perform unsupervised learning using meta learning with CACTUs. In the concluding chapters, you will work through recent trends in meta learning such as adversarial meta learning, task agnostic meta learning, and meta imitation learning. By the end of this book, you will be familiar with state-of-the-art meta learning algorithms and able to enable human-like cognition for your machine learning models. Hands-On Meta Learning with Python is for machine learning enthusiasts, AI researchers, and data scientists who want to explore meta learning as an advanced approach for training machine learning models. Working knowledge of machine learning concepts and Python programming is necessary.

226 pages, Paperback

Published December 31, 2018

Reviews

[Xianshun Chen · Rating 4 out of 5]

This is by far the best book i have for few-shot learning and meta-learning. The explanation is succinct and to the point and the code is easy to understand. I particularly like the chapters on MAML, ADML, Reptile and gradient agreement. The matching network, relation network and prototypical network is also helping me to better understand those learnt models. The caveat is that the codes were implemented in Tensorflow 1 and i had to re-implemented them in Tensorflow 2 and keras to understand how they work. Also some bug found in the prototypical network source codes which i had to fix to get it work.