Neural networks (NNs) and deep learning (DL) currently provide the best solutions to many problems in image recognition, speech recognition, natural language processing, control and precision health. NN and DL make the artificial intelligence (AI) much closer to human thinking modes. However, there are many open problems related to DL in NN, e.g.: convergence, learning efficiency, optimality, multi-dimensional learning, on-line adaptation. This requires to create new algorithms and analysis methods. Practical applications both require and stimulate this development.
There's no question artificial intelligence and machine learning technologies are enabling important discoveries in healthcare, but there can be a bit of a disconnect among the various stakeholders using them. A panel discussion at the upcoming CNS Summit in Boca Raton, Fla. presents a rare opportunity to bring the parties together and foster collaboration.
As evidenced by the articles in this special issue, transfer learning has come a long way in the past five or so years, partially because of DARPA's Transfer Learning program, which sponsored much of the work reported in this issue. There is a Transfer Learning Toolkit for Matlab available on the web. Transfer learning has developed techniques for classification, regression, and clustering (as summarized in Pan and Yang's 2009 survey) and for complex interactive tasks that are often best addressed by reinforcement learning techniques. However, there is a more practical and more feasible goal for transfer learning against which progress is being made. An engineering-oriented goal of artificial intelligence that could be enabled by transfer learning is the ability to construct a large number of diverse applications not from scratch, but by taking advantage of knowledge already acquired and formally represented for other purposes.
Its goal is to capture, in a general form, the internal structure of the objects, relations, strategies, and processes used to solve tasks drawn from a source domain, and exploit that knowledge to improve performance in a target domain. A Note from the AI Magazine Editor in Chief: Part Two of the Structured Knowledge Transfer special issue will be published in the summer 2011 issue (volume 32 number 2) of AI Magazine. Articles in this issue will include: "Knowledge Transfer between Automated Planners," by Susana Fernández, Ricardo Aler, and Daniel Borrajo "Transfer Learning by Reusing Structured Knowledge," by Qiang Yang, Vincent W. Zheng, Bin Li, and Hankz Hankui Zhuo "An Application of Transfer to American Football: From Observation of Raw Video to Control in a Simulated Environment," by David J. Stracuzzi, Alan Fern, Kamal Ali, Robin Hess, Jervis Pinto, Nan Li, Tolga Könik, and Dan Shapiro "Toward a Computational Model of Transfer," by Daniel Oblinger While the field of psychology has studied transfer learning in people for many years, AI has only recently taken up the challenge. The topic received initial attention with work on inductive transfer in the 1990s, while the number of workshops and conferences has noticeably increased in the last five years. This special issue represents the state of the art in the subarea of transfer learning that focuses on the acquisition and reuse of structured knowledge.
We selected them for significance, novelty, and (in several cases) common task focus. Every year, AI Magazine devotes one fourth of its annual production to a special issue based on the Innovative Applications of Artificial Intelligence (IAAI) conference. Because IAAI is the premier venue for documenting the transition of AI technology into application, these special issues provide a snapshot of the state of the art in AI with the practical syllogism in mind; they present work that has value because it delivers value in use. As a result, it is good to read these articles from a practical perspective. Papers that document deployed systems clarify the motivating application constraints, the match (and mismatch) between problems and technology, the innovations required to surmount barriers to deployment, and the impact of technology on application through practical measures of cost and benefit.
The Workshop on Connectionist-Symbolic Integration: From Unified to Hybrid Approaches was held on 19 to 20 August 1995 in Montreal, Canada, in conjunction with the Fourteenth International Joint Conference on Artificial Intelligence. The focus of the workshop was on learning and architectures that feature hybrid representations and support hybrid learning. The general consensus was that hybrid connectionist-symbolic models constitute a promising avenue to the development of more robust, more powerful, and more versatile architectures for both cognitive modeling and intelligent systems. The workshop was cochaired by myself and Frederic Alexandre. It featured 23 presentations, including 2 invited talks and 2 panel discussions.
In this and the next issue of AI Magazine, we will present extended versions of papers presented at IAAI-12 (held in Toronto, Ontario, Canada) that were selected for their description of AI technologies that are either in practical use or close to it. We also present an article by Ramon Lopez de Mantaras based on his 2011 Robert S. Engelmore Memorial Lecture. Our selections for this issue begin with Playing with Cases: Rendering Expressive Music with Case-Based Reasoning by Ramon Lopez de Mantaras and Josep Lluís Arcos, based on the Robert S. Engelmore Memorial Lecture at IAAI-11 in San Francisco, California. Lopez de Mantaras received the Robert S. Engelmore Memorial Lecture Award for his pioneering research contributions in a breadth of artificial intelligence areas, especially pattern recognition and case-based reasoning, leading to novel applications in design, diagnosis, and music, and for extensive international leadership and service for the AI community. He is also a founding member of several AI companies.
Cover: AI@50--We Are Golden, by James Gary, New York, New York. What Do We Know About Knowledge? Send all submissions to AI Magazine, AAAI, 445 Burgess Drive, Menlo Park, CA 94025-3442. Electronic submissions should be submitted using the web-based submissions form. Submissions information is available at aimagazine.org. Although no particular style is required for submissions, electronic submissions must be in PDF form. Authors whose work is accepted for publication, will be required to revise their work to conform reasonably to AI Magazine styles. If an article is accepted for publication, a new electronic copy will also be required. Although AI Ma ga zine generally grants great deference to an author's work the Magazine retains the right to determine the final published form of every article. Calendar items should be posted electronically (at least one month prior to the event or deadline). News items should be sent to the News Editor, AI Magazine, 445 Burgess Drive, Menlo Park, CA 94025-3442. Please do not send news releases via either email or fax, and do not send news releases to any of the other editors. Web-based job postings can be made using the job bank submissions form at aimagazine.org. Replacement copies (for current issue only) are available upon written request and a check for $10.00. Back issues are also available (cost may differ). Send replacement or back order requests to AAAI. Microform copies are available from ProQuest Information and Learning, 300 North Zeeb Road, Ann Arbor, MI 48106.
In this issue of AI Magazine, we continue our presentation of extended versions of papers presented at IAAI-12 (held in Toronto, Ontario, Canada) that were selected for their description of AI technologies that are in practical use. Our selections for this issue describe deployed applications. They explain the context, requirements, and constraints of the application, how the technology was adapted to satisfy those factors, and the impact that this innovation brought to the operation in terms of cost and performance. The articles also supply useful insights into use cases that we hope can also be translated to other work that the AI community is engaged in. In the first of these deployed application articles, eBird: A Human/Computer Learning Network to Improve Biodiversity Conservation and Research by Steve Kelling, Carl Lagoze, Weng-Keen Wong, Jun Yu, Theodoros Damoulas, Jeff Gerbracht, Daniel Fink, and Carla Gomes, the authors describe an intriguing application that successfully combines the best in human and artificial computing capabilities with an active feedback loop between people and machines.
Workshop Report The 1994 Workshop on Case-Based Reasoning (CBR) focused on the evaluation of CBR theories, models, systems, and system components. The CBR community addressed the evaluation of theories and implemented systems, with the consensus that a balance between novel innovations and evaluations could maximize progress. The 4 invited talks, 14 paper presentations, 19 poster presentations, and 1 summary panel discussion were attended by 66 participants. The four invited speakers discussed how CBR approaches can be evaluated in research projects, industrial applications, and military tasks. Katia Sycara (Carnegie Mellon University [CMU]) outlined an exhaustive set of measures for evaluating CBR systems and discussed how she applied some of these measures in empirical comparisons with other approaches for solving job shop scheduling problems.