A Connectionist Framework for Reasoning: Reasoning with Examples

We present a connectionist architecture that supports almost instantaneous deductive and abductive reasoning. The deduction algorithm responds in few steps for single rule queries and in general, takes time that is linear with the number of rules in the query. The abduction algorithm produces an explanation in few steps and the best explanation in time linear with the size of the assumption set. The size of the network is polynomially related to the size of other representations of the domain, and may even be smaller. We base our connectionist model on Valiant's Neuroidal model (Val94) and thus make minimal assumptions about the computing elements, which are assumed to be classical threshold elements with states. Within this model we develop a reasoning framework that utilizes a model-based approach to reasoning (KKS93; KR94b). In particular, we suggest to interpret the connectionist architecture as encoding examples of the domain we reason about and show how to perform various reasoning tasks with this interpretation. We then show that the representations used can be acquired efficiently from interactions with the environment and discuss how this learning process influences the reasoning performance of the network.

[1]  Bart Selman,et al.  Reasoning With Characteristic Models , 1993, AAAI.

[2]  Lokendra Shastri,et al.  An Optimally Efficient Limited Inference System , 1990, AAAI.

[3]  P. Johnson-Laird.  Mental models , 1989 .

[4]  Bart Selman,et al.  Model-Preference Default Theories , 1990, Artif. Intell..

[5]  Marco Cadoli.  Tractable Reasoning in Artificial Intelligence , 1995, Lecture Notes in Computer Science.

[6]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, CACM.

[7]  Dan Roth,et al.  Reasoning with Models , 1994, Artif. Intell..

[8]  Michael G. Dyer,et al.  High-level Inferencing in a Connectionist Network , 1989 .

[9]  L. Shastri,et al.  From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony , 1993, Behavioral and Brain Sciences.

[10]  Hector J. Levesque,et al.  The Tractability of Subsumption in Frame-Based Description Languages , 1984, AAAI.

[11]  J. Fodor,et al.  Connectionism and cognitive architecture: A critical analysis , 1988, Cognition.

[12]  Leslie G. Valiant,et al.  Circuits of the mind , 1994 .

[13]  Dan Roth,et al.  Learning to reason , 1994, JACM.

[14]  Dan Roth,et al.  Default-Reasoning with Models , 1995, IJCAI.

[15]  Steven Minton,et al.  Solving Large-Scale Constraint-Satisfaction and Scheduling Problems Using a Heuristic Repair Method , 1990, AAAI.

[16]  Steffen Hölldobler,et al.  On the Adequateness of the Connection Method , 1993, AAAI.

[17]  Dan Roth,et al.  Learning to Reason: The Non-Monotonic Case , 1995, IJCAI.

[18]  Dan Roth,et al.  On the Hardness of Approximate Reasoning , 1993, IJCAI.

[19]  S. Kosslyn.  Image and mind , 1982 .

[20]  Lokendra Shastri,et al.  A Computational Model of Tractable Reasoning - Taking Inspiration from Cognition , 1993, IJCAI.

[21]  Ron Sun,et al.  Robust Reasoning: Integrating Rule-Based and Similarity-Based Reasoning , 1995, Artif. Intell..

[22]  Hector J. Levesque,et al.  A New Method for Solving Hard Satisfiability Problems , 1992, AAAI.

[23]  Geoffrey E. Hinton,et al.  Learning and relearning in Boltzmann machines , 1986 .

[24]  John McCarthy,et al.  Programs with common sense , 1960 .

[25]  Gadi Pinkas,et al.  Reasoning, Nonmonotonicity and Learning in Connectionist Networks that Capture Propositional Knowledge , 1995, Artif. Intell..

[26]  Mark Derthick,et al.  Mundane Reasoning by Settling on a Plausible Model , 1990, Artif. Intell..