万本电子书0元读

万本电子书0元读

顶部广告

Hands-On Meta Learning with Python电子书

售       价:¥

46人正在读 | 0人评论 6.2

作       者:Sudharsan Ravichandiran

出  版  社:Packt Publishing

出版时间:2018-12-31

字       数:22.7万

所属分类: 进口书 > 外文原版书 > 电脑/网络

温馨提示:数字商品不支持退换货,不提供源文件,不支持导出打印

为你推荐

  • 读书简介
  • 目录
  • 累计评论(0条)
  • 读书简介
  • 目录
  • 累计评论(0条)
Explore a diverse set of meta-learning algorithms and techniques to enable human-like cognition for your machine learning models using various Python frameworks Key Features *Understand the foundations of meta learning algorithms *Explore practical examples to explore various one-shot learning algorithms with its applications in TensorFlow *Master state of the art meta learning algorithms like MAML, reptile, meta SGD Book Description 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. What you will learn *Understand the basics of meta learning methods, algorithms, and types *Build voice and face recognition models using a siamese network *Learn the prototypical network along with its variants *Build relation networks and matching networks from scratch *Implement MAML and Reptile algorithms from scratch in Python *Work through imitation learning and adversarial meta learning *Explore task agnostic meta learning and deep meta learning Who this book is for 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.
目录展开

Title Page

Copyright and Credits

Hands-On Meta Learning with Python

Dedication

About Packt

Why subscribe?

Packt.com

Contributors

About the author

About the reviewers

Packt is searching for authors like you

Preface

Who this book is for

What this book covers

To get the most out of this book

Download the example code files

Conventions used

Get in touch

Reviews

Introduction to Meta Learning

Meta learning

Meta learning and few-shot

Types of meta learning

Learning the metric space

Learning the initializations

Learning the optimizer

Learning to learn gradient descent by gradient descent

Optimization as a model for few-shot learning

Summary

Questions

Further reading

Face and Audio Recognition Using Siamese Networks

What are siamese networks?

Architecture of siamese networks

Applications of siamese networks

Face recognition using siamese networks

Building an audio recognition model using siamese networks

Summary

Questions

Further readings

Prototypical Networks and Their Variants

Prototypical networks

Algorithm

Performing classification using prototypical networks

Gaussian prototypical network

Algorithm

Semi-prototypical networks

Summary

Questions

Further reading

Relation and Matching Networks Using TensorFlow

Relation networks

Relation networks in one-shot learning

Relation networks in few-shot learning

Relation networks in zero-shot learning

Loss function

Building relation networks using TensorFlow

Matching networks

Embedding functions

The support set embedding function (g)

The query set embedding function (f)

The architecture of matching networks

Matching networks in TensorFlow

Summary

Questions

Further reading

Memory-Augmented Neural Networks

NTM

Reading and writing in NTM

Read operation

Write operation

Erase operation

Add operation

Addressing mechanisms

Content-based addressing

Location-based addressing

Interpolation

Convolution shift

Sharpening

Copy tasks using NTM

Memory-augmented neural networks (MANN)

Read and write operations

Read operation

Write operation

Summary

Questions

Further reading

MAML and Its Variants

MAML

MAML algorithm

MAML in supervised learning

Building MAML from scratch

Generate data points

Single layer neural network

Training using MAML

MAML in reinforcement learning

Adversarial meta learning

FGSM

ADML

Building ADML from scratch

Generating data points

FGSM

Single layer neural network

Adversarial meta learning

CAML

CAML algorithm

Summary

Questions

Further reading

Meta-SGD and Reptile

Meta-SGD

Meta-SGD for supervised learning

Building Meta-SGD from scratch

Generating data points

Single layer neural network

Meta-SGD

Meta-SGD for reinforcement learning

Reptile

The Reptile algorithm

Sine wave regression using Reptile

Generating data points

Two-layered neural network

Reptile

Summary

Questions

Further readings

Gradient Agreement as an Optimization Objective

Gradient agreement as an optimization

Weight calculation

Algorithm

Building gradient agreement algorithm with MAML

Generating data points

Single layer neural network

Gradient agreement in MAML

Summary

Questions

Further reading

Recent Advancements and Next Steps

Task agnostic meta learning (TAML)

Entropy maximization/reduction

Algorithm

Inequality minimization

Inequality measures

Gini coefficient

Theil index

Variance of algorithms

Algorithm

Meta imitation learning

MIL algorithm

CACTUs

Task generation using CACTUs

Learning to learn in concept space

Key components

Concept generator

Concept discriminator

Meta learner

Loss function

Concept discrimination loss

Meta learning loss

Algorithm

Summary

Questions

Further reading

Assessments

Chapter 1: Introduction to Meta Learning

Chapter 2: Face and Audio Recognition Using Siamese Networks

Chapter 3: Prototypical Networks and Their Variants

Chapter 4: Relation and Matching Networks Using TensorFlow

Chapter 5: Memory-Augmented Neural Networks

Chapter 6: MAML and Its Variants

Chapter 7: Meta-SGD and Reptile Algorithms

Chapter 8: Gradient Agreement as an Optimization Objective

Chapter 9: Recent Advancements and Next Steps

Other Books You May Enjoy

Leave a review - let other readers know what you think

累计评论(0条) 2个书友正在讨论这本书 发表评论

发表评论

发表评论,分享你的想法吧!

买过这本书的人还买过

读了这本书的人还在读

回顶部