Is there one central mechanism upon which all human thinking rests? Cognitive scientists Douglas Hofstadter and Emmanuel Sander argue that there is. At this core is our incessant proclivity to take what we perceive, to abstract it, and to find resemblances to prior experiences—in other words, our ability to make analogies. In The Essence of Thought , Hofstadter and Sander show how analogy-making pervades our thought at all levels—indeed, that we make analogies not once a day or once an hour, but many times per second. Thus, analogy is the mechanism that, silently and hidden, chooses our words and phrases for us when we speak, frames how we understand the most banal everyday situation, guides us in unfamiliar situations, and gives rise to great acts of imagination. We categorize because of analogies that range from simple to subtle, and thus our categories, throughout our lives, expand and grow ever more fluid. Through examples galore and lively prose peppered, needless to say, with analogies large and small, Hofstadter and Sander offer us a new way of thinking about thinking.

This revolutionary book provides fresh answers to long-standing questions of human origins and consciousness. Drawing on his breakthrough research in comparative neuroscience, Terrence Deacon offers a wealth of insights into the significance of symbolic thinking: from the co-evolutionary exchange between language and brains over two million years of hominid evolution to the ethical repercussions that followed man's newfound access to other people's thoughts and emotions. Informing these insights is a new understanding of how Darwinian processes underlie the brain's development and function as well as its evolution. In contrast to much contemporary neuroscience that treats the brain as no more or less than a computer, Deacon provides a new clarity of vision into the mechanism of mind. It injects a renewed sense of adventure into the experience of being human.

Machine learning is one of the fastest growing areas of computer science, with far-reaching applications. The aim of this textbook is to introduce machine learning, and the algorithmic paradigms it offers, in a principled way. The book provides an extensive theoretical account of the fundamental ideas underlying machine learning and the mathematical derivations that transform these principles into practical algorithms. Following a presentation of the basics of the field, the book covers a wide array of central topics that have not been addressed by previous textbooks. These include a discussion of the computational complexity of learning and the concepts of convexity and stability; important algorithmic paradigms including stochastic gradient descent, neural networks, and structured output learning; and emerging theoretical concepts such as the PAC-Bayes approach and compression-based bounds. Designed for an advanced undergraduate or beginning graduate course, the text makes the fundamentals and algorithms of machine learning accessible to students and non-expert readers in statistics, computer science, mathematics, and engineering.

As the power of computing has grown over the past few decades, the field of machine learning has advanced rapidly in both theory and practice. Machine learning methods are usually based on the assumption that the data generation mechanism does not change over time. Yet real-world applications of machine learning, including image recognition, natural language processing, speech recognition, robot control, and bioinformatics, often violate this common assumption. Dealing with non-stationarity is one of modern machine learning's greatest challenges. This book focuses on a specific non-stationary environment known as covariate shift, in which the distributions of inputs (queries) change but the conditional distribution of outputs (answers) is unchanged, and presents machine learning theory, algorithms, and applications to overcome this variety of non-stationarity. After reviewing the state-of-the-art research in the field, the authors discuss topics that include learning under covariate shift, model selection, importance estimation, and active learning. They describe such real world applications of covariate shift adaption as brain-computer interface, speaker identification, and age prediction from facial images. With this book, they aim to encourage future research in machine learning, statistics, and engineering that strives to create truly autonomous learning machines able to learn under non-stationarity.

In this wide-ranging book, the author presents his critique of the contemporary portrayal of cognition, an analysis of the conceptual foundations of cognitive science and a proposal for a new concept of the mind. Shanon argues that the representational account is seriously lacking and that far from serving as a basis of cognitive activity, representations are the products of such activity. He proposes an alternative view of the mind in which the basic capability of the cognitive system is not the manipulation of symbols but rather action in the world. His book offers a different outlook on the phenomenon of consciousness and presents a new conception of psychological theory and explanation.

A Pentagon defense expert and former U.S. Army Ranger explores what it would mean to give machines authority over the ultimate decision of life or death.
What happens when a Predator drone has as much autonomy as a Google car? Or when a weapon that can hunt its own targets is hacked? Although it sounds like science fiction, the technology already exists to create weapons that can attack targets without human input. Paul Scharre, a leading expert in emerging weapons technologies, draws on deep research and firsthand experience to explore how these next-generation weapons are changing warfare.
Scharre’s far-ranging investigation examines the emergence of autonomous weapons, the movement to ban them, and the legal and ethical issues surrounding their use. He spotlights artificial intelligence in military technology, spanning decades of innovation from German noise-seeking Wren torpedoes in World War II―antecedents of today’s homing missiles―to autonomous cyber weapons, submarine-hunting robot ships, and robot tank armies. Through interviews with defense experts, ethicists, psychologists, and activists, Scharre surveys what challenges might face "centaur warfighters" on future battlefields, which will combine human and machine cognition. We’ve made tremendous technological progress in the past few decades, but we have also glimpsed the terrifying mishaps that can result from complex automated systems―such as when advanced F-22 fighter jets experienced a computer meltdown the first time they flew over the International Date Line.
At least thirty countries already have defensive autonomous weapons that operate under human supervision. Around the globe, militaries are racing to build robotic weapons with increasing autonomy. The ethical questions within this book grow more pressing each day. To what extent should such technologies be advanced? And if responsible democracies ban them, would that stop rogue regimes from taking advantage? At the forefront of a game-changing debate, Army of None engages military history, global policy, and cutting-edge science to argue that we must embrace technology where it can make war more precise and humane, but without surrendering human judgment. When the choice is life or death, there is no replacement for the human heart.

TensorFlow是谷歌2015年开源的主流深度学习框架，目前已在谷歌、优步（Uber）、京东、小米等科技公司广泛应用。《Tensorflow实战》为使用TensorFlow深度学习框架的入门参考书，旨在帮助读者以最快、最有效的方式上手TensorFlow和深度学习。书中省略了深度学习繁琐的数学模型推导，从实际应用问题出发，通过具体的TensorFlow样例程序介绍如何使用深度学习解决这些问题。《Tensorflow实战》包含了深度学习的入门知识和大量实践经验，是走进这个最新、最火的人工智能领域的首选参考书。

《21 个项目玩转深度学习——基于TensorFlow 的实践详解》以实践为导向，深入介绍了深度学习技术和TensorFlow 框架编程内容。
通过本书，读者可以训练自己的图像识别模型、进行目标检测和人脸识别、完成一个风格迁移应用，还可以使用神经网络生成图像和文本，进行时间序列预测、搭建机器翻译引擎，训练机器玩游戏。全书共包含21 个项目，分为深度卷积网络、RNN网络、深度强化学习三部分。读者可以在自己动手实践的过程中找到学习的乐趣，了解算法和编程框架的细节，让学习深度学习算法和TensorFlow 的过程变得轻松和高效。本书代码基于TensorFlow 1.4 及以上版本，并介绍了TensorFlow 中的一些新特性。
本书适合有一定机器学习基础的学生、研究者或从业者阅读，尤其是希望深入研究TensorFlow 和深度学习算法的数据工程师，也适合对人工智能、深度学习感兴趣的在校学生，以及希望进入大数据应用的研究者。

Appropriate for upper-division undergraduate- and graduate-level courses in computer vision found in departments of Computer Science, Computer Engineering and Electrical Engineering. This long anticipated book is the most complete treatment of modern computer vision methods by two of the leading authorities in the field. This accessible presentation gives both a general view of the entire computer vision enterprise and also offers sufficient detail for students to be able to build useful applications. Students will learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods.

Designed for students, scientists and engineers interested in learning about the core ideas of vision science, this volume brings together the broad range of data and theory accumulated in this field. The book consists of three sections and an appendix. The first section consists of an introduction and three chapters that describe image encoding. These chapters review optical image formation by the cornea and lens retinal sampling and wavelength-encoding by the photoreceptors. The text's second section consists of four chapters on image representation. The third section reviews how to interpret images in terms of objects. This section features two chapters that review computational and experimental studies of colour appearance, then motion and depth. These chapters are followed by a chapter with many demonstrations concerning object perception. Topics such as colour appearance, cortical colour-blindness, motion flow, motion appearance, motion physiology and visual illusions are also included in this part of the book. "Foundations of Science" is suitable for courses on vision science in psychology, neuroscience, engineering or computer science departments, and is suitable for upper-level undergraduates and graduate students. The text contains special study exercises at the end of most chapters. The questions aim to enrich the main material and point the way to additional material in the literature. Finally, the book has an appendix consisting of four parts: an introduction to linear systems methods; a discussion of monitor calibration; an introduction to Bayesian classifiers; and a discussion of optic flow computation.

In 1982, Springer published the English translation of the Russian book Estimation of Dependencies Based on Empirical Data which became the foundation of the statistical theory of learning and generalization (the VC theory). A number of new principles and new technologies of learning, including SVM technology, have been developed based on this theory. The second edition of this book contains two parts: - A reprint of the first edition which provides the classical foundation of Statistical Learning Theory - Four new chapters describing the latest ideas in the development of statistical inference methods. They form the second part of the book entitled Empirical Inference Science The second part of the book discusses along with new models of inference the general philosophical principles of making inferences from observations. It includes new paradigms of inference that use non-inductive methods appropriate for a complex world, in contrast to inductive methods of inference developed in the classical philosophy of science for a simple world. The two parts of the book cover a wide spectrum of ideas related to the essence of intelligence: from the rigorous statistical foundation of learning models to broad philosophical imperatives for generalization. The book is intended for researchers who deal with a variety of problems in empirical inference: statisticians, mathematicians, physicists, computer scientists, and philosophers.

"A dizzying display of intellect and wild imaginings by Moravec, a world-class roboticist who has himself developed clever beasts . . . Undeniably, Moravec comes across as a highly knowledgeable and creative talent--which is just what the field needs".--Kirkus Reviews.

How deep learning -- from Google Translate to driverless cars to personal cognitive assistants -- is changing our lives and transforming every sector of the economy.
The deep learning revolution has brought us driverless cars, the greatly improved Google Translate, fluent conversations with Siri and Alexa, and enormus profits from automated trading on the New York Stock Exchange. Deep learning networks can play poker better than professional poker players and defeat a world champion at Go. In this book, Terry Sejnowski explains how deep learning went from being an arcane academic field to a disruptive technology in the information economy.
Sejnowski played an important role in the founding of deep learning, as one of a small group of researchers in the 1980s who challenged the prevailing logic-and-symbol based version of AI. The new version of AI Sejnowski and others developed, which became deep learning, is fueled instead by data. Deep networks learn from data in the same way that babies experience the world, starting with fresh eyes and gradually acquiring the skills needed to navigate novel environments. Learning algorithms extract information from raw data; information can be used to create knowledge; knowledge underlies understanding; understanding leads to wisdom. Someday a driverless car will know the road better than you do and drive with more skill; a deep learning network will diagnose your illness; a personal cognitive assistant will augment your puny human brain. It took nature many millions of years to evolve human intelligence; AI is on a trajectory measured in decades. Sejnowski prepares us for a deep learning future.

An examination of metaphor in poetry as a microcosm of the human imagination—a way to understand the mechanisms of creativity.
In The Spider's Thread, Keith Holyoak looks at metaphor as a microcosm of the creative imagination. Holyoak, a psychologist and poet, draws on the perspectives of thinkers from the humanities—poets, philosophers, and critics—and from the sciences—psychologists, neuroscientists, linguists, and computer scientists. He begins each chapter with a poem—by poets including Samuel Taylor Coleridge, Sylvia Plath, Walt Whitman, Emily Dickinson, Robert Frost, Theodore Roethke, Du Fu, William Butler Yeats, and Pablo Neruda—and then widens the discussion to broader notions of metaphor and mind.
Holyoak uses Whitman's poem “A Noiseless Patient Spider” to illustrate the process of interpreting a poem, and explains the relevance of two psychological mechanisms, analogy and conceptual combination, to metaphor. He outlines ideas first sketched by Coleridge—who called poetry “the best words in their best order”—and links them to modern research on the interplay between cognition and emotion, controlled and associative thinking, memory and creativity. Building on Emily Dickinson's declaration “the brain is wider than the sky,” Holyoak suggests that the control and default networks in the brain may combine to support creativity. He also considers, among other things, the interplay of sound and meaning in poetry; symbolism in the work of Yeats, Jung, and others; indirect communication in poems; the mixture of active and passive processes in creativity; and whether artificial intelligence could ever achieve poetic authenticity. Guided by Holyoak, we can begin to trace the outlines of creativity through the mechanisms of metaphor.

The presentation of a novel theory in orthogonal regression The literature about neural-based algorithms is often dedicated to principal component analysis (PCA) and considers minor component analysis (MCA) a mere consequence. Breaking the mold, Neural-Based Orthogonal Data Fitting is the first book to start with the MCA problem and arrive at important conclusions about the PCA problem. The book proposes several neural networks, all endowed with a complete theory that not only explains their behavior, but also compares them with the existing neural and traditional algorithms. EXIN neurons, which are of the authors' invention, are introduced, explained, and analyzed. Further, it studies the algorithms as a differential geometry problem, a dynamic problem, a stochastic problem, and a numerical problem. It demonstrates the novel aspects of its main theory, including its applications in computer vision and linear system identification. The book shows both the derivation of the TLS EXIN from the MCA EXIN and the original derivation, as well as: Shows TLS problems and gives a sketch of their history and applications Presents MCA EXIN and compares it with the other existing approaches Introduces the TLS EXIN neuron and the SCG and BFGS acceleration techniques and compares them with TLS GAO Outlines the GeTLS EXIN theory for generalizing and unifying the regression problems Establishes the GeMCA theory, starting with the identification of GeTLS EXIN as a generalization eigenvalue problem In dealing with mathematical and numerical aspects of EXIN neurons, the book is mainly theoretical. All the algorithms, however, have been used in analyzing real-time problems and show accurate solutions. Neural-Based Orthogonal Data Fitting is useful for statisticians, applied mathematics experts, and engineers.