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

Memory-augmented neural networks (MANN)

Now we will see an interesting variant of NTM, called MANN. It is extensively used for one-shot learning tasks. MANN is designed to make NTM perform better at one-shot learning tasks. We know that NTM can either use content-based addressing or location-based addressing. But in MANN, we use only content-based addressing.

MANN uses a new addressing scheme called least recently used access. As the name suggests, it writes to the least recently used memory location. Wait. What? We just learned that MANN is not location-based, so why are we writing to the least recently used location? This is because the least recently used memory location is determined by the read operation and the read operation is performed by content-based addressing. So, we basically perform content-based addressing for reading and write to the location that was least recently used.

Read and write operations

Now we will see how to perform read and write operations in MANN and how they...