Skip navigation

Computer Science and Intelligent Systems

Computer Science and Intelligent Systems

  • Page 4 of 85
A Concise History

The history of computing could be told as the story of hardware and software, or the story of the Internet, or the story of “smart” hand-held devices, with subplots involving IBM, Microsoft, Apple, Facebook, and Twitter. In this concise and accessible account of the invention and development of digital technology, computer historian Paul Ceruzzi offers a broader and more useful perspective.

Foundations and Algorithms

Boosting is an approach to machine learning based on the idea of creating a highly accurate predictor by combining many weak and inaccurate “rules of thumb.” A remarkably rich theory has evolved around boosting, with connections to a range of topics, including statistics, game theory, convex optimization, and information geometry. Boosting algorithms have also enjoyed practical success in such fields as biology, vision, and speech processing. At various times in its history, boosting has been perceived as mysterious, controversial, even paradoxical.

Pixels, Numbers, and Programs

This book explores image processing from several perspectives: the creative, the theoretical (mainly mathematical), and the programmatical. It explains the basic principles of image processing, drawing on key concepts and techniques from mathematics, psychology of perception, computer science, and art, and introduces computer programming as a way to get more control over imaging processing operations. It does so without requiring college-level mathematics or prior programming experience.

In Adversarial Design, Carl DiSalvo examines the ways that technology design can provoke and engage the political. He describes a practice, which he terms “adversarial design,” that uses the means and forms of design to challenge beliefs, values, and what is taken to be fact. It is not simply applying design to politics--attempting to improve governance for example, by redesigning ballots and polling places; it is implicitly contestational and strives to question conventional approaches to political issues.

In development for thirty years, Soar is a general cognitive architecture that integrates knowledge-intensive reasoning, reactive execution, hierarchical reasoning, planning, and learning from experience, with the goal of creating a general computational system that has the same cognitive abilities as humans. In contrast, most AI systems are designed to solve only one type of problem, such as playing chess, searching the Internet, or scheduling aircraft departures.

The Commodore Amiga

Long ago, in 1985, personal computers came in two general categories: the friendly, childish game machine used for fun (exemplified by Atari and Commodore products); and the boring, beige adult box used for business (exemplified by products from IBM). The game machines became fascinating technical and artistic platforms that were of limited real-world utility. The IBM products were all utility, with little emphasis on aesthetics and no emphasis on fun. Into this bifurcated computing environment came the Commodore Amiga 1000.

Introduction to Covariate Shift Adaptation

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.

Building Computers That Understand Speech

Stanley Kubrick’s 1968 film 2001: A Space Odyssey famously featured HAL, a computer with the ability to hold lengthy conversations with his fellow space travelers. More than forty years later, we have advanced computer technology that Kubrick never imagined, but we do not have computers that talk and understand speech as HAL did. Is it a failure of our technology that we have not gotten much further than an automated voice that tells us to “say or press 1”?

An Ecological Approach to Information Behavior

Human information interaction (HII) is an emerging area of study that investigates how people interact with information; its subfield human information behavior (HIB) is a flourishing, active discipline. Yet despite their obvious relevance to the design of information systems, these research areas have had almost no impact on systems design. One issue may be the contextual complexity of human interaction with information; another may be the difficulty in translating real-life and unstructured HII complexity into formal, linear structures necessary for systems design.

Evidence-Based Social Design

Online communities are among the most popular destinations on the Internet, but not all online communities are equally successful. For every flourishing Facebook, there is a moribund Friendster--not to mention the scores of smaller social networking sites that never attracted enough members to be viable. This book offers lessons from theory and empirical research in the social sciences that can help improve the design of online communities.

  • Page 4 of 85