Machine learning draws on multiple disciplines. Mitchell provides the necessary background in both statistics and computational learning theory (a chapter on each) so that results from these fields can be understood and applied. He does not go overboard and overwhelm students in these areas. Instead, Mitchell takes the practical point of view. Students are provided with enough information to understand and use results from these ancillary fields.

All this adds up to a fluent and entertaining reading experience. Partly, the research surveyed in this book can already be considered classical; for example, the extensive coverage of human stereo vision is mostly based on Marr's (1982) seminal account of the subject. However, the experimental psychology research that is reviewed in the book is relatively recent. Many of the ideas that Pinker presents have been in the air in evolutionary psychology; particularly influential and much cited in this book are the studies of Cosmides and Tooby (1994). Pinker's own contribution is to boldly combine all these ideas into a united theory of the mind and its origins.

This article presents an overview and survey of current work in case-based reasoning (CBR) integrations. There has been a recent upsurge in the integration of CBR with other reasoning modalities and computing paradigms, especially rule-based reasoning (RBR) and constraint-satisfaction problem (CSP) solving. CBR integrations with modelbased reasoning (MBR), genetic algorithms, and information retrieval are also discussed. This article characterizes the types of multimodal reasoning integrations where CBR can play a role, identifies the types of roles that CBR components can fulfill, and provides examples of integrated CBR systems. Past progress, current trends, and issues for future research are discussed. This article presents a brief introduction to CBR, a review of other approaches with which CBR has been combined, an overview of tasks CBR integrations can perform, a discussion of open issues in CBR integration, and a look at synergies achieved through CBR integration.

Society's expectation regarding the capabilities and intelligence of such systems has also grown. We have become a more complicated society with more complicated problems. As the expectation of intelligent systems rises, we discover many more applications for AI. Additionally, as the difficulty level and computational requirements of such problems rise, there is a need to distribute the problem solving. Although the field of multiagent systems and distributed AI is relatively young, the importance and applicability of this technology for solving today's problems continues to grow.

Czerwinski, Mary, see Nguyen, Trung 1992 AAAI Robot Exhibition and Competition see Dean, Thomas 1992 Workshop on Design Rationale Capture and Use, The, see Lee, Jintae Advances in Real-Time Expert System Technologies, see Barachini, Franz AI and Creativity: 1993 Spring Symposium Report, see Kim, Steven AI and N&Hard Problems: 1993 Spring Symposium Report, see Crawford, James AI Research and Application Development at Boeing's Huntsville Laboratories see Tanner, Steve Anick, Peter; and Simoudis, Evange-10s. Agent Architectures, see Hanks, Steve Berman, Jay I. see Wright, Jon R. Bonasso, R. Peter see Dean, Thomas Bookman, Lawrence, see Sun, Ron Brown, Karen E. see Wright, Jon R. Building Lexicons Two Winner see Congdon, Clare Carnes, Ray, see Tanner, Steve Case-Based Reasoning and Information Retrieval: 1993 Spring Symposium Report, see Anick, Peter Chandrasekaran, B.; Narayanan, N. Hari; and Iwasaki, Yumi. Charniak, Eugene, see Goldman, Robert l? Chien, Steve, see Gat, Erann. Cohen, Paul R., see Hanks, Steve Compaq Quicksource: Providing the Consumer with the Power Drummond, Mark, see Lansky, Amy Engineering Design through Constraint-Based Reasoning, see Murtagh, Niall Etzioni, Oren. Goal-Driven Learning: Fundamental Issues: A Symposium Report, see Leake, David Goldman, Robert l?; Charniak, Eugene; Gale, William; and Norvig, Peter.

Bylaws of the American Association for Artificial Intelligence, 13(1): Spring 1992, A2-A9 Adler, Mark see Rewari, Anil. Anick, Peter see Rewari, Anil. Architecture for Real-Time Distributed Scheduling, An, 13(3): Fall 1992, 46-56. Billmers, Meyer see Rewari, Anil. Bylaws of the American Association for Artificial Intelligence, 13(1): Spring 1992, A2-A9 Cambridge Center for Behavioral Studies see Weintraub, Joseph.

See Artificial Intelligence zn Canada: A Review. See Steamer: an Interactive Inspectable Samulation-Based Trazning System Wilensky, Robert.

See Toward the Principled Enganeering of Knowledge. Expert Systems: Where are we? And where do we go from here? Feigenbaum, Edward A, See Signal-to-symbol transformation: HASP/SIAP case study. Research in Progress Vol IV, No. 4, p. 58, Winter, 1983 THE AI MAGAZINE Spring 1984 83 K Minsky, Marvin Why People Think Computers Can't.

This editorial introduction provides an overview of artificial intelligence for computational sustainability, and introduces the next two special issue articles that will appear in AI Magazine. The emerging interdisciplinary field of computational sustainability (Gomes 2009) draws techniques from computer science, information science, mathematics, statistics, operations research, and related disciplines to help balance environmental and socioeconomic needs for sustainable development. Artificial intelligence (AI) techniques play a key role in computational sustainability research, enabling the solution of sustainability problems that involve modeling or decision making in dynamic and uncertain environments. Since 2011, the main AAAI conference has included a special track on computational sustainability, encouraging AI research in this area and broader participation of sustainability researchers in the AAAI community. Sustainable solutions must balance between environmental, societal, and economic demands (United Nations General Assembly 2005).

There is a critically important dialogue going on across the extended global automotive industry about the future evolution of transportation and mobility. This debate is driven by the convergence of a series of industry-changing forces and mega-trends (see figure 1). Innovative technologies are changing how companies develop and build vehicles. Electric and fuel-cell powertrains tend to offer greater propulsion for lower energy investment at lower emission levels.1 New, lightweight materials enable automakers to reduce vehicle weight without sacrificing passenger safety.2 Further breakthroughs are advancing the introduction of autonomous vehicles; increasingly, daily news reports suggest that driverless cars will soon become a commercial reality.3 We have already seen rapid advances in the "connected car--?--innovations that integrate communications technologies and the Internet of Things to provide valuable services to drivers.4