Knowledge Infusion

The question of how machines can be endowed with the ability to acquire and robustly manipulate commonsense knowledge is a fundamental scientific problem. Here we formulate an approach to this problem that we call knowledge infusion. We argue that robust logic offers an appropriate semantics for this endeavor because it supports provably efficient algorithms for a basic set of necessary learning and reasoning tasks. We observe that multiple concepts can be learned simultaneously from a common data set in a data efficient manner. We also point out that the preparation of appropriate teaching materials for training systems constructed according to these principles raises new challenges.

[1]  Leslie G. Valiant,et al.  Robust logics , 1999, STOC '99.

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

[3]  Sebastiaan Terwijn,et al.  Probabilistic Logic and Induction , 2005, J. Log. Comput..

[4]  Nick Littlestone,et al.  From on-line to batch learning , 1989, COLT '89.

[5]  David Haussler,et al.  Learnability and the Vapnik-Chervonenkis dimension , 1989, JACM.

[6]  J. R. Quinlan.  Learning Logical Definitions from Relations , 1990 .

[7]  Leslie G. Valiant,et al.  Computational limitations on learning from examples , 1988, JACM.

[8]  Dan Roth,et al.  On Kernel Methods for Relational Learning , 2003, ICML.

[9]  Leslie G. Valiant,et al.  A neuroidal architecture for cognitive computation , 1998, ICALP.

[10]  Leslie G. Valiant,et al.  Cryptographic Limitations on Learning Boolean Formulae and Finite Automata , 1993, Machine Learning: From Theory to Applications.

[11]  Dan Roth,et al.  A Winnow-Based Approach to Context-Sensitive Spelling Correction , 1998, Machine Learning.

[12]  David Haussler,et al.  Occam's Razor , 1987, Inf. Process. Lett..

[13]  Saso Dzeroski,et al.  Learning Nonrecursive Definitions of Relations with LINUS , 1991, EWSL.

[14]  Peter A. Flach,et al.  Propositionalization approaches to relational data mining , 2001 .

[15]  Leslie G. Valiant,et al.  Learning Disjunction of Conjunctions , 1985, IJCAI.

[16]  David Haussler,et al.  Learning Conjunctive Concepts in Structural Domains , 1989, Machine Learning.

[17]  G. A. Miller.  THE PSYCHOLOGICAL REVIEW THE MAGICAL NUMBER SEVEN, PLUS OR MINUS TWO: SOME LIMITS ON OUR CAPACITY FOR PROCESSING INFORMATION 1 , 1956 .

[18]  Dan Roth,et al.  Learning with Feature Description Logics , 2002, ILP.

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

[20]  Dan Roth,et al.  Relational Learning via Propositional Algorithms: An Information Extraction Case Study , 2001, IJCAI.

[21]  Leslie G. Valiant,et al.  Relational Learning for NLP using Linear Threshold Elements , 1999, IJCAI.

[22]  A. Miyake,et al.  Models of Working Memory: Mechanisms of Active Maintenance and Executive Control , 1999 .

[23]  Dale Schuurmans,et al.  Sequential PAC learning , 1995, COLT '95.

[24]  A. Newell.  Unified Theories of Cognition , 1990 .

[25]  N. Littlestone.  Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[26]  Leslie G. Valiant,et al.  A general lower bound on the number of examples needed for learning , 1988, COLT '88.