Genetic programming may be more powerful than neural networks and other machine learning techniques, able to solve problems in a wider range of disciplines. In this ground-breaking book, John Koza shows how this remarkable paradigm works and provides substantial empirical evidence that solutions to a great variety of problems from many different fields can be found by genetically breeding populations of computer programs. Genetic Programming contains a great many worked examples and includes a sample computer code that will allow readers to run their own programs.In getting computers to solve problems without being explicitly programmed, Koza stresses two points: that seemingly different problems from a variety of fields can be reformulated as problems of program induction, and that the recently developed genetic programming paradigm provides a way to search the space of possible computer programs for a highly fit individual computer program to solve the problems of program induction. Good programs are found by evolving them in a computer against a fitness measure instead of by sitting down and writing them.John R. Koza is Consulting Associate Professor in the Computer Science Department at Stanford University.

- Presents the life's work of a Nobel Laureate and internationally recognised leader in the field
- Builds new bridges between physics and biology
- Provides a physical basis for Darwin's principle of natural selection
- Presents a new theory of information including semantics
This book presents a vivid argument for the almost lost idea of a unity of all natural sciences. It starts with the "strange" physics of matter, including particle physics, atomic physics and quantum mechanics, cosmology, relativity and their consequences (Chapter I), and it continues by describing the properties of material systems that are best understood by statistical and phase-space concepts (Chapter II). These lead to entropy and to the classical picture of quantitative information, initially devoid of value and meaning (Chapter III). Finally, "information space" and dynamics within it are introduced as a basis for semantics (Chapter IV), leading to an exploration of life and thought as new problems in physics (Chapter V).
Dynamic equations - again of a strange (but very general) nature - bring about the complex familiarity of the world we live in. Surprising new results in the life sciences open our eyes to the richness of physical thought, and they show us what can and what cannot be explained by a Darwinian approach. The abstract physical approach is applicable to the origins of life, of meaningful information and even of our universe.

http://neuralnetworksanddeeplearning.com/

本书精心策划了三个虚拟项目，将数据科学家必需的专业技能融合其中，教会读者如何将数据存储到计算机内存中，如何在必要的时候转换内存中的数据值，如何用R编写自己的程序并将其用于数据分析和模拟运行。读者将跟随世界一流的RStudio培训师掌握宝贵的编程技能，并借助这些技能成为优秀的数据科学家。

【技术大咖推荐】
“很荣幸担任这本优秀图书的技术审校。这本书能帮助很多中级Python程序员掌握这门语言，我也从中学到了相当多的知识！”——Alex Martelli，Python软件基金会成员
“对于想要扩充知识的中级和高级Python程序员来说，这本书是充满了实用编程技巧的宝藏。”——Daniel Greenfeld和Audrey Roy Greenfeld，Two Scoops of Django作者
【本书特色】
本书由奋战在Python开发一线近20年的Luciano Ramalho执笔，Victor Stinner、Alex Martelli等Python大咖担纲技术审稿人，从语言设计层面剖析编程细节，兼顾Python 3和Python 2，告诉你Python中不亲自动手实践就无法理解的语言陷阱成因和解决之道，教你写出风格地道的Python代码。
● Python数据模型：理解为什么特殊方法是对象行为一致的关键。
● 数据结构：充分利用内置类型，理解Unicode文本和字节二象性。
● 把函数视作对象：把Python函数视作一等对象，并了解这一点对流行的设计模式的影响。
● 面向对象习惯用法：通过构建类学习引用、可变性、接口、运算符重载和多重继承。
● 控制流程：学习使用上下文管理器、生成器、协程，以及通过concurrent.futures和asyncio包实现的并发。
● 元编程：理解特性、描述符、类装饰器和元类的工作原理。
【主要内容】
本书致力于帮助Python开发人员挖掘这门语言及相关程序库的优秀特性，避免重复劳动，同时写出简洁、流畅、易读、易维护，并且具有地道Python风格的代码。本书尤其深入探讨了Python语言的高级用法，涵盖数据结构、Python风格的对象、并行与并发，以及元编程等不同的方面。
本书适合中高级Python软件开发人员阅读参考。
【译者简介】
安道
专注于现代计算机技术的自由翻译，译有《Flask Web 开发》《Python 网络编程攻略》《Ruby on Rails 教程》等书。
个人网站：http://about.ac/。
吴珂
现为Airbnb公司软件工程师，所在团队主要负责开发和维护各类可伸缩、高性能服务，并在Airbnb内推广面向服务的系统架构。在分布式系统、云存储服务和跨平台SDK开发，以及大规模数据处理等方面有多年经验。

本书旨在向读者交付有关深度学习的交互式学习体验。书中不仅阐述深度学习的算法原理，还演示它们的实现和运行。与传统图书不同，本书的每一节都是一个可以下载并运行的 Jupyter记事本，它将文字、公式、图像、代码和运行结果结合在了一起。此外，读者还可以访问并参与书中内容的讨论。
全书的内容分为3个部分：第一部分介绍深度学习的背景，提供预备知识，并包括深度学习最基础的概念和技术；第二部分描述深度学习计算的重要组成部分，还解释近年来令深度学习在多个领域大获成功的卷积神经网络和循环神经网络；第三部分评价优化算法，检验影响深度学习计算性能的重要因素，并分别列举深度学习在计算机视觉和自然语言处理中的重要应用。
本书同时覆盖深度学习的方法和实践，主要面向在校大学生、技术人员和研究人员。阅读本书需要读者了解基本的Python编程或附录中描述的线性代数、微分和概率基础。

本书由Keras之父、现任Google人工智能研究员的弗朗索瓦•肖莱（François Chollet）执笔，详尽介绍了用Python和Keras进行深度学习的探索实践，涉及计算机视觉、自然语言处理、生成式模型等应用。书中包含30多个代码示例，步骤讲解详细透彻。由于本书立足于人工智能的可达性和大众化，读者无须具备机器学习相关背景知识即可展开阅读。在学习完本书后，读者将具备搭建自己的深度学习环境、建立图像识别模型、生成图像和文字等能力。

本书多年来一直深受世界各国高校师生的欢迎，是美国哈佛大学、麻省理工学院、普林斯顿大学、加州大学伯克利分校等许多著名大学的首选教材，对我国的高校教学也产生了广泛影响。
本 书以历史眼光，从发展的角度、当前的水平以及现阶段的研究方向等几个方面，全景式描绘了计算机科学各个子学科的主要领域。在内容编排上，本书很好地兼顾了 学科广度和主题深度，把握了最新的技术趋势。本书用算法、数据抽象等核心思想贯穿各个主题，并且充分展现了历史背景、发展历程和新的技术趋势，培养读者的 大局观，为其今后深入学习其他计算机专业课程打下坚实的基础。
本书深入浅出、图文并茂，内容引人入胜，极易引发读者的兴趣，绝无一般教材的枯燥和晦涩。此外，本书的教学手段多样、习题丰富，并且每章后都附有与本章内容相关的社会现实问题供读者思考和讨论，这些都很好地体现了作者强调培养学生分析问题能力的教学理念。
第11版新增了手持移动设备，特别是智能手机的相关内容，主要涉及第3章（操作系统）、第4章（组网）、第6章（编程语言）和第7章（软件工程）中。此外，书中还对软件所有权和责任、训练人工神经网络等许多相关内容做了更新，以反映最新技术面貌。

本书是理论计算机科学领域的名作，是计算机科学核心主题的导论性教材。全书分为可计算性、文法与自动机、逻辑学、复杂性及语义学5个部分，分别讲述了可计算性理论、形式语言、逻辑学与自动演绎、可计算复杂性（包括NP完全问题）和编程语言的语义等主题，并展示了它们之间如何相互关联。.
本书是计算机及相关专业高年级本科生和研究生的理想教学参考书，对于计算机领域的专业人士也是很好的技术参考书。

本书是最权威的计算机体系结构著作，是久负盛名的经典作品。书中系统地介绍了计算机系统的设计基础、指令集系统结构、流水线和指令集并行技术、层次化存储系统与存储设备、互连网络以及多处理器系统等重要内容。在这个最新版中，作者增加了当前炙手可热的云计算和手机客户端技术等相关内容，探讨了在手机、平板电脑、笔记本电脑和其他移动计算设备上云计算的软硬件实现方式。

图论导引，ISBN：9787115161536，作者：（美）沙特朗、张萍

This book explores the intersection between cognitive sciences and social sciences. In particular, it explores the intersection between individual cognitive modeling and modeling of multi-agent interaction (social stimulation). The two contributing fields - individual cognitive modeling (especially cognitive architectures) and modeling of multi-agent interaction (including social simulation and, to some extent, multi-agent systems) - have seen phenomenal growth in recent years. However, the interaction of these two fields has not been sufficiently developed. We believe that the interaction of the two may be more significant than either alone. They bring with them enormous intellectual capitals. These intellectual capitals can be profitably leveraged in creating true synergy between the two fields, leading to more in-depth studies and better understanding of both individual cognition and sociocultural processes. It is possible that an integrative field of study in cognitive and social sciences is emerging and we are laying the foundation for it.

What makes people smarter than computers? These volumes by a pioneering neurocomputing group suggest that the answer lies in the massively parallel architecture of the human mind. They describe a new theory of cognition called connectionism that is challenging the idea of symbolic computation that has traditionally been at the center of debate in theoretical discussions about the mind. The authors' theory assumes the mind is composed of a great number of elementary units connected in a neural network. Mental processes are interactions between these units which excite and inhibit each other in parallel rather than sequential operations. In this context, knowledge can no longer be thought of as stored in localized structures; instead, it consists of the connections between pairs of units that are distributed throughout the network. Volume 1 lays the foundations of this exciting theory of parallel distributed processing, while Volume 2 applies it to a number of specific issues in cognitive science and neuroscience, with chapters describing models of aspects of perception, memory, language, and thought.

Genetic algorithms are founded upon the principle of evolution, i.e., survival of the fittest. Hence evolution programming techniques, based on genetic algorithms, are applicable to many hard optimization problems, such as optimization of functions with linear and nonlinear constraints, the traveling salesman problem, and problems of scheduling, partitioning, and control. The importance of these techniques is still growing, since evolution programs are parallel in nature, and parallelism is one of the most promising directions in computer science.
The book is self-contained and the only prerequisite is basic undergraduate mathematics. This third edition has been substantially revised and extended by three new chapters and by additional appendices containing working material to cover recent developments and a change in the perception of evolutionary computation.

'This book covers the dominant theoretical approaches to the approximate solution of hard combinatorial optimization and enumeration problems. It contains elegant combinatorial theory, useful and interesting algorithms, and deep results about the intrinsic complexity of combinatorial problems. Its clarity of exposition and excellent selection of exercises will make it accessible and appealing to all those with a taste for mathematics and algorithms' - Richard Karp, University Professor, University of California at Berkeley. Following the development of basic combinatorial optimization techniques in the 1960s and 1970s, a main open question was to develop a theory of approximation algorithms. In the 1990s, parallel developments in techniques for designing approximation algorithms as well as methods for proving hardness of approximation results have led to a beautiful theory. The need to solve truly large instances of computationally hard problems, such as those arising from the Internet or the human genome project, has also increased interest in this theory. The field is currently very active, with the toolbox of approximation algorithm design techniques getting always richer. It is a pleasure to recommend Vijay Vazirani's well-written and comprehensive book on this important and timely topic. "I am sure the reader will find it most useful both as an introduction to approximability as well as a reference to the many aspects of approximation algorithms' - Laszlo Lovasz, Senior Researcher, Microsoft Research.

本书是国际算法大师乌迪·曼博（Udi Manber）博士撰写的一本享有盛誉的著作。全书共分12章：第1章到第4章为介绍性内容，涉及数学归纳法、算法分析、数据结构等内容；第5章提出了与归纳证明进行类比的算法设计思想；第6章到第9章分别给出了4个领域的算法，如序列和集合的算法、图算法、几何算法、代数和数值算法；第10章涉及归约，也是第11章的序幕，而后者涉及NP完全问题；第12章则介绍了并行算法；最后是部分习题的答案及参考文献。本书的特色有二，旨在提高读者的问题求解能力，使读者能够理解算法设计的过程和思想：一是强调算法设计的创造性过程，注重算法设计背后的创造性思想，而不拘泥于某个具体算法的详细讨论；二是将算法设计类比于定理归纳证明，揭示了算法设计的基本思想和本质。
本书的组织结构清晰且易于理解，强调了创造性，具有浓郁特色，时至今日仍有其巨大的价值，并且适合作为计算机及相关专业算法和高级算法课程的教材。

本书是关于操作系统的权威教材。大多数关于操作系统的图书均重理论而轻实践，而本书则在这两者之间进行了较好的折中。本册详细探讨了操作系统的基本原理，包括进程、进程间通信、信号量、管程、消息传递、调度算法、输入、输出、死锁、设备驱动程序、存储管理、调页算法、文件系统设计、安全和保护机制等；此外，还详细讨论了一个特殊的操作系统MINIX 3（一个与UNIX兼容的操作系统），并提供了该系统的源代码（见本书下册），以便于读者仔细研究。这种安排不仅可让读者了解操作系统的基本原理，而且可让读者了解到这些基本原理是如何应用到真实的操作系统中去的。
本书适用于高校计算机专业的学生，也可供程序设计人员、工程技术人员、系统架构师等相关人员参考。

The P-NP problem is the most important open problem in computer science, if not all of mathematics. The Golden Ticket provides a nontechnical introduction to P-NP, its rich history, and its algorithmic implications for everything we do with computers and beyond. In this informative and entertaining book, Lance Fortnow traces how the problem arose during the Cold War on both sides of the Iron Curtain, and gives examples of the problem from a variety of disciplines, including economics, physics, and biology. He explores problems that capture the full difficulty of the P-NP dilemma, from discovering the shortest route through all the rides at Disney World to finding large groups of friends on Facebook. But difficulty also has its advantages. Hard problems allow us to safely conduct electronic commerce and maintain privacy in our online lives. The Golden Ticket explores what we truly can and cannot achieve computationally, describing the benefits and unexpected challenges of the P-NP problem.