Evolutionary Deep Learning: Genetic Algorithms and Neural Networks

Discover one-of-a-kind AI strategies never before seen outside of academic papers! Learn how the principles of evolutionary computation overcome deep learning's common pitfalls and deliver adaptable model upgrades without constant manual adjustment.

Summary

In Evolutionary Deep Learning you will learn how to:

 

• Solve complex design and analysis problems with evolutionary computation
• Tune deep learning hyperparameters with evolutionary computation (EC), genetic algorithms, and particle swarm optimization
• Use unsupervised learning with a deep learning autoencoder to regenerate sample data
• Understand the basics of reinforcement learning and the Q-Learning equation
• Apply Q-Learning to deep learning to produce deep reinforcement learning
• Optimize the loss function and network architecture of unsupervised autoencoders
• Make an evolutionary agent that can play an OpenAI Gym game

Evolutionary Deep Learning is a guide to improving your deep learning models with AutoML enhancements based on the principles of biological evolution. This exciting new approach utilizes lesser-known AI approaches to boost performance without hours of data annotation or model hyperparameter tuning. In this one-of-a-kind guide, you'll discover tools for optimizing everything from data collection to your network architecture.

Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.

About the technology
Deep learning meets evolutionary biology in this incredible book. Explore how biology-inspired algorithms and intuitions amplify the power of neural networks to solve tricky search, optimization, and control problems. Relevant, practical, and extremely interesting examples demonstrate how ancient lessons from the natural world are shaping the cutting edge of data science.

About the book
Evolutionary Deep Learning introduces evolutionary computation (EC) and gives you a toolbox of techniques you can apply throughout the deep learning pipeline. Discover genetic algorithms and EC approaches to network topology, generative modeling, reinforcement learning, and more! Interactive Colab notebooks give you an opportunity to experiment as you explore.

What's inside

 

• Solve complex design and analysis problems with evolutionary computation
• Tune deep learning hyperparameters
• Apply Q-Learning to deep learning to produce deep reinforcement learning
• Optimize the loss function and network architecture of unsupervised autoencoders
• Make an evolutionary agent that can play an OpenAI Gym game

About the reader
For data scientists who know Python.

About the author
Micheal Lanham is a proven software and tech innovator with over 20 years of experience.

Table of Contents
PART 1 - GETTING STARTED
1 Introducing evolutionary deep learning
2 Introducing evolutionary computation
3 Introducing genetic algorithms with DEAP
4 More evolutionary computation with DEAP
PART 2 - OPTIMIZING DEEP LEARNING
5 Automating hyperparameter optimization
6 Neuroevolution optimization
7 Evolutionary convolutional neural networks
PART 3 - ADVANCED APPLICATIONS
8 Evolving autoencoders
9 Generative deep learning and evolution
10 NEAT: NeuroEvolution of Augmenting Topologies
11 Evolutionary learning with NEAT
12 Evolutionary machine learning and beyond

發現從未在學術論文以外見過的獨特人工智慧策略！學習如何運用演化計算原理克服深度學習的常見問題，並在不斷手動調整的情況下提供可適應的模型升級。

摘要

在《演化深度學習》中，您將學習以下內容：

• 使用演化計算解決複雜的設計和分析問題
• 使用演化計算（EC）、遺傳算法和粒子群優化調整深度學習的超參數
• 使用深度學習自編碼器進行無監督學習以重建樣本數據
• 了解強化學習的基礎知識和Q-Learning方程式
• 將Q-Learning應用於深度學習以產生深度強化學習
• 優化無監督自編碼器的損失函數和網絡架構
• 創建一個能夠玩OpenAI Gym遊戲的演化智能體

《演化深度學習》是一本基於生物演化原理的AutoML增強技術，用於改進深度學習模型的指南。這種令人興奮的新方法利用較少人知的人工智慧方法來提升性能，而無需花費數小時進行數據標註或模型超參數調整。在這本獨一無二的指南中，您將發現從數據收集到網絡架構的一切優化工具。

購買印刷版書籍將包含Manning Publications提供的PDF、Kindle和ePub格式的免費電子書。

關於技術
這本令人難以置信的書將深度學習與演化生物學相結合。探索受生物學啟發的算法和直覺如何增強神經網絡解決棘手的搜索、優化和控制問題。相關、實用且極其有趣的示例展示了自然界的古老教訓如何塑造數據科學的前沿。

關於本書
《演化深度學習》介紹了演化計算（EC）並為您提供了一套可以在整個深度學習流程中應用的技術工具。探索遺傳算法和EC方法在網絡拓撲、生成建模、強化學習等方面的應用！互動的Colab筆記本讓您有機會在探索中進行實驗。

內容簡介

• 使用演化計算解決複雜的設計和分析問題
• 調整深度學習的超參數
• 將Q-Learning應用於深度學習以產生深度強化學習
• 優化無監督自編碼器的損失函數和網絡架構
• 創建一個能夠玩OpenAI Gym遊戲的演化智能體

讀者對象
適合具備Python知識的數據科學家。

關於作者
Micheal Lanham 是一位經驗豐富的軟體和技術創新者，擁有超過20年的經驗。

目錄
第1部分 - 入門
1 演化深度學習介紹
2 演化計算介紹
3 使用DEAP介紹遺傳算法
4 更多DEAP的演化計算
第2部分 - 優化深度學習
5 自動化超參數優化
6 神經演化優化
7 演化卷積神經網絡
第3部分 - 高級應用
8 演化自編碼器
9 生成式深度學習和演化
10 NEAT：增強拓撲的神經演化
11 使用NEAT的演化學習
12 演化機器學習及更多內容

Micheal Lanham is a proven software and tech innovator with over 20 years of experience. He has developed a broad range of software applications in areas such as games, graphics, web, desktop, engineering, artificial intelligence, GIS, and machine learning applications for a variety of industries. At the turn of the millennium, Micheal began working with neural networks and evolutionary algorithms in game development.

Micheal Lanham 是一位經驗豐富的軟體和科技創新者，擁有超過20年的經驗。他在遊戲、圖形、網頁、桌面、工程、人工智慧、地理資訊系統和機器學習等領域開發了各種軟體應用程式，服務於多個行業。在千禧年之際，Micheal 開始在遊戲開發中使用神經網路和演化算法。