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


We have seen how MAML finds the optimal initial parameter of a model so that it can easily be adaptable to a new task with fewer gradient steps. Now, we will see an interesting variant of MAML called CAML. The idea of CAML is very simple, same as MAML; it also tries to find the better initial parameter. We learned how MAML uses two loops; on the inner loop, MAML learns the parameter specific to the task and tries to minimize the loss using gradient descent and, on the outer loop, it updates the model parameter to reduce the expected loss across several tasks so that we can use the updated model parameter as better initializations for related tasks.

In CAML, we perform a very small tweak to the MAML algorithm. Here, instead of using a single model parameter, we split our model parameter into two:

  • Context parameter: It is task-specific parameter updated on the inner loop. It is denoted by∅ and it is specific to each task and represents the embeddings of an individual task.
  • Shared parameter...