Book Image

Hands-On One-shot Learning with Python

By : Shruti Jadon, Ankush Garg
Book Image

Hands-On One-shot Learning with Python

By: Shruti Jadon, Ankush Garg

Overview of this book

One-shot learning has been an active field of research for scientists trying to develop a cognitive machine that mimics human learning. With this book, you'll explore key approaches to one-shot learning, such as metrics-based, model-based, and optimization-based techniques, all with the help of practical examples. Hands-On One-shot Learning with Python will guide you through the exploration and design of deep learning models that can obtain information about an object from one or just a few training samples. The book begins with an overview of deep learning and one-shot learning and then introduces you to the different methods you can use to achieve it, such as deep learning architectures and probabilistic models. Once you've got to grips with the core principles, you'll explore real-world examples and implementations of one-shot learning using PyTorch 1.x on datasets such as Omniglot and MiniImageNet. Finally, you'll explore generative modeling-based methods and discover the key considerations for building systems that exhibit human-level intelligence. By the end of this book, you'll be well-versed with the different one- and few-shot learning methods and be able to use them to build your own deep learning models.

Related Content you might be interested in

Current Title:

Small book image
Hands-On One-shot Learning with Python
Shruti Jadon | Ankush Garg
Apr, 2020 | 156 pages
Small book image
Hands-On Meta Learning with Python
Sudharsan Ravichandiran
Dec, 2018 | 226 pages
Small book image
Hands-On Mathematics for Deep Learning
Jay Dawani
Jun, 2020 | 364 pages
Small book image
Advanced Deep Learning with Python
Ivan Vasilev
Dec, 2019 | 468 pages
Table of Contents (11 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
1
Section 1: One-shot Learning Introduction
Section 1: One-shot Learning Introduction
Free Chapter
2
Introduction to One-shot Learning
Introduction to One-shot Learning
Technical requirements
The human brain – overview
Machine learning – historical overview
One-shot learning – overview
Setting up your environment
Coding exercise
Summary
Questions
3
Section 2: Deep Learning Architectures
Section 2: Deep Learning Architectures
4
Metrics-Based Methods
Metrics-Based Methods
Technical requirements
Parametric methods – an overview
Understanding Siamese networks
Understanding matching networks
Coding exercise
Summary
Questions
Further reading
5
Model-Based Methods
Model-Based Methods
Technical requirements
Understanding Neural Turing Machines
Memory-augmented neural networks
Understanding meta networks
Coding exercises
Summary
Questions
Further reading
6
Optimization-Based Methods
Optimization-Based Methods
Technical requirements
Overview of gradient descent
Understanding model-agnostic meta-learning
Understanding LSTM meta-learner
Exercises
Summary
Questions
Further reading
7
Section 3: Other Methods and Conclusion
Section 3: Other Methods and Conclusion
8
Generative Modeling-Based Methods
Generative Modeling-Based Methods
Technical requirements
Overview of Bayesian learning
Understanding directed graphical models
Overview of probabilistic methods
Bayesian program learning
Discriminative k-shot learning
Summary
Further reading
9
Conclusions and Other Approaches
Conclusions and Other Approaches
Recent advancements
Related fields
Applications
Further reading
10
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Understanding directed graphical models

We will now study directed graphical models briefly before we delve into probabilistic models for one-shot learning. A directed graphical model (also known as a Bayesian network) is defined with random variables connected with directed edges, as in the parent-child relationship. One such Bayesian network is shown in the following diagram:

The joint distribution over random variables in this graph S, R, L, W, and T can be broken into multiple distributions by a simple chain rule:

The conditional distributions on the right side of the preceding equation have a large number of parameters. This is because each distribution is conditioned on many variables and each conditioned variable has its own outcome space. This effect is even more prominent if we go further down in the graph when we have a huge set of conditioned variables. Consequently...

Previous Section
End of Section 4
Next Section