由于机器学习，自动驾驶汽车、自然语言识别和在线推荐引擎都成为可能。现在，您可以创建自己的遗传算法、受自然启发的群集、蒙特卡罗模拟、细胞自动机和群集。了解如何测试您的ML代码，并深入探讨更高级的主题。如果你是一个初学者到中级程序员热衷于了解机器学习，这本书是为你准备的。
使用一些自包含的方法发现机器学习算法。建立一系列算法，发现普遍适用的术语和方法。在你的算法中加入智能，引导他们发现问题的好解决方案。
在这本书中，你将
使用启发式和设计适应度函数。
建立遗传算法。
用蚂蚁、蜜蜂和微粒组成大自然的蜂群。
创建蒙特卡罗模拟。
研究细胞自动机。
通过爬山和模拟退火找到最小值和最大值。
尝试选择方法，包括锦标赛和轮盘赌。
了解启发式、适应度函数、度量和集群。
测试你的代码，激发灵感去尝试新问题。通过各种场景编码你走出一个纸袋；对于任何有能力的程序员来说，这是一项重要的技能。通过创建每个问题的可视化，了解算法是如何探索和学习的。获得灵感，设计自己的机器学习项目，熟悉术语。
你需要什么
C++中的代码（>＝C++ 11）、Python（2 x或3 x）和JavaScript（使用HTML5画布）。还使用matplotlib和一些开源库，包括SFML、Catch和Cosmic Ray。这些绘图和测试库不是必需的，但它们的使用将为您提供更全面的体验。只要为您选择的语言配备一个文本编辑器和编译器/解释器，您仍然可以根据一般算法描述编写代码。
Genetic Algorithms and Machine Learning for Programmers: Create AI Models and Evolve Solutions (AZW3)
Self-driving cars, natural language recognition, and online recommendation engines are all possible thanks to Machine Learning. Now you can create your own genetic algorithms, nature-inspired swarms, Monte Carlo simulations, cellular automata, and clusters. Learn how to test your ML code and dive into even more advanced topics. If you are a beginner-to-intermediate programmer keen to understand machine learning, this book is for you.
Discover machine learning algorithms using a handful of self-contained recipes. Build a repertoire of algorithms, discovering terms and approaches that apply generally. Bake intelligence into your algorithms, guiding them to discover good solutions to problems.
In this book, you will
Use heuristics and design fitness functions.
Build genetic algorithms.
Make nature-inspired swarms with ants, bees and particles.
Create Monte Carlo simulations.
Investigate cellular automata.
Find minima and maxima, using hill climbing and simulated annealing.
Try selection methods, including tournament and roulette wheels.
Learn about heuristics, fitness functions, metrics, and clusters.
Test your code and get inspired to try new problems. Work through scenarios to code your way out of a paper bag; an important skill for any competent programmer. See how the algorithms explore and learn by creating visualizations of each problem. Get inspired to design your own machine learning projects and become familiar with the jargon.
What You Need
Code in C++ (>= C++11), Python (2.x or 3.x) and JavaScript (using the HTML5 canvas). Also uses matplotlib and some open source libraries, including SFML, Catch and Cosmic-Ray. These plotting and testing libraries are not required but their use will give you a fuller experience. Armed with just a text editor and compiler/interpreter for your language of choice you can still code along from the general algorithm descriptions.
OR
