Marvin Minsky, one of the pioneers of artificial intelligence and a renowned mathematicial and computer scientist, died on Sunday, 24 January 2016 of a cerebral hemmorhage. In this article, AI scientists Kenneth D. Forbus (Northwestern University), Benjamin Kuipers (University of Michigan), and Henry Lieberman (Massachusetts Institute of Technology) recall their interactions with Minksy and briefly recount the impact he had on their lives and their research. A remembrance of Marvin Minsky was held at the AAAI Spring Symposium at Stanford University on March 22. Video remembrances of Minsky by Danny Bobrow, Benjamin Kuipers, Ray Kurzweil, Richard Waldinger, and others can be on the sentient webpage1 or on youtube.com.
Useful feedback makes use of models of domain-specific knowledge, especially models that are commonly held by potential students. To empirically determine what these models are, student data can be clustered to reveal common misconceptions or common problem-solving strategies. We use this approach to cluster a corpus of hand-drawn student sketches to discover common answers.
We report on a series of transfer learning experiments in game domains, in which we use structural analogy from one learned game to speed learning of another related game. We find that a major benefit of analogy is that it reduces the extent to which the source domain must be generalized before transfer. We describe two techniques in particular, minimal ascension and metamapping, that enable analogies to be drawn even when comparing descriptions using different relational vocabularies. Evidence for the effectiveness of these techniques is provided by a large-scale external evaluation, involving a substantial number of novel distant analogs.
Forbus, Kenneth D., Hinrichs, Thomas R.
We are developing Companion Cognitive Systems, a new kind of software that can be effectively treated as a collaborator. Aside from their potential utility, we believe this effort is important because it focuses on three key problems that must be solved to achieve human-level AI: Robust reasoning and learning, interactivity, and longevity. We describe the ideas we are using to develop the first architecture for Companions: analogical processing, grounded in cognitive science for reasoning and learning, sketching and concept maps to improve interactivity, and a distributed agent architecture hosted on a cluster to achieve performance and longevity. We outline some results on learning by accumulating examples derived from our first experimental version.
Learning how to create, test, and revise models is a central skill in scientific reasoning. We argue that qualitative modeling provides an appropriate level of representation for helping middle-school students learn to become modelers. We describe Vmodel, a system we have created that uses visual representations and that enables middle-school students to create qualitative models. We discuss the design of the visual representation language, how Vmodel works, and evidence from school studies that indicate it is successful in helping students.
Sketch maps are an important spatial representation used in many geospatial-reasoning tasks. This article describes techniques we have developed that enable software to perform humanlike reasoning about sketch maps. We illustrate the utility of these techniques in the context of nuSketch Battlespace, a research system that has been successfully used in a variety of experiments. After an overview of the nuSketch approach and nuSketch Battlespace, we outline the representations of glyphs and sketches and the nuSketch spatial reasoning architecture.
Bredeweg, Bert, Forbus, Kenneth D.
We argue that qualitative modeling provides a valuable way for students to learn. Two modelbuilding environments, VMODEL and HOMER/- VISIGARP, are presented that support learners by constructing conceptual models of systems and their behavior using qualitative formalisms. Both environments use diagrammatic representations to facilitate knowledge articulation. Preliminary evaluations in educational settings provide support for the hypothesis that qualitative modeling tools can be valuable aids for learning.
Karlgren, Jussi, Kanerva, Pentti, Gamback, Bjorn, Forbus, Kenneth D., Tumer, Kagan, Stone, Peter, Goebel, Kai, Sukhatme, Gaurav S., Balch, Tucker, Fischer, Bernd, Smith, Doug, Harabagiu, Sanda, Chaudri, Vinay, Barley, Mike, Guesgen, Hans, Stahovich, Thomas, Davis, Randall, Landay, James
The Association for the Advancement of Artificial Intelligence, in cooperation with Stanford University's Department of Computer Science, presented the 2002 Spring Symposium Series, held Monday through Wednesday, 25 to 27 March 2002, at Stanford University. The nine symposia were entitled (1) Acquiring (and Using) Linguistic (and World) Knowledge for Information Access; (2) Artificial Intelligence and Interactive Entertainment; (3) Collaborative Learning Agents; (4) Information Refinement and Revision for Decision Making: Modeling for Diagnostics, Prognostics, and Prediction; (5) Intelligent Distributed and Embedded Systems; (6) Logic-Based Program Synthesis: State of the Art and Future Trends; (7) Mining Answers from Texts and Knowledge Bases; (8) Safe Learning Agents; and (9) Sketch Understanding.
Forbus, Kenneth D.
The goal of intelligent computer-aided engineering (ICAE) is to construct computer programs that capture a significant fraction of an engineer's knowledge. Today, ICAE systems are a goal, not a reality. We begin by examining several scenarios of what ICAE systems could be like. Next we describe why ICAE won't evolve directly from current applications of expert system technology to engineering problems.