Book Image

Hands-On Meta Learning with Python

By : Sudharsan Ravichandiran
Book Image

Hands-On Meta Learning with Python

By: Sudharsan Ravichandiran

Overview of this book

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.
Table of Contents (17 chapters)
Title Page
About Packt


In this chapter, we've learned about TAML for reducing the task bias. We saw two types of methods: entropy-based and inequality-based TAML. Then, we explored meta imitation learning, which combines meta learning with imitation learning. We saw how meta learning helps imitation learning to learn from fewer imitations.We also saw how to apply model agnostic meta learning in an unsupervised learning setting using CACTUS.Then, we explored a deep meta learning algorithm called learning to learn in concept space. We saw how meta learning can be boosted by the power of deep learning.

Meta learning is one of the most interesting branches in the field of AI; now that you've understood various meta learning algorithms, you can start building meta learning models that are generalizable across various tasks and contribute to meta learning research.