Neural-Symbolic Learning
Neural networks and symbolic learning techniques can be seen as operating at different levels of abstraction. Our work focuses on understanding differences between their capabilities, and on combining their strengths.
People
Leif Johnson Ph.D. Student leif@cs.utexas.edu
Publications (11)
Combining Symbolic and Connectionist Learning Methods to Refine Certainty-Factor Rule-Bases 1996
J. Jeffrey Mahoney
Revising Bayesian Network Parameters Using Backpropagation 1996
Sowmya Ramachandran and Raymond J. Mooney
Refinement of Bayesian Networks by Combining Connectionist and Symbolic Techniques 1995
Sowmya Ramachandran
Comparing Methods For Refining Certainty Factor Rule-Bases 1994
J. Jeffrey Mahoney and Raymond J. Mooney
Modifying Network Architectures For Certainty-Factor Rule-Base Revision 1994
J. Jeffrey Mahoney and Raymond J. Mooney
Combining Connectionist and Symbolic Learning to Refine Certainty-Factor Rule-Bases 1993
J. Jeffrey Mahoney and Raymond J. Mooney
Combining Symbolic and Neural Learning to Revise Probabilistic Theories 1992
J. Jeffrey Mahoney and Raymond J. Mooney
Growing Layers of Perceptrons: Introducing the Extentron Algorithm 1992
Paul T. Baffes and John M. Zelle
Symbolic and Neural Learning Algorithms: An Experimental Comparison 1991
J.W. Shavlik, Raymond J. Mooney and G. Towell
An Experimental Comparison of Symbolic and Connectionist Learning Algorithms 1989
Raymond J. Mooney, J.W. Shavlik, G. Towell and A. Gove
Processing Issues in Comparisons of Symbolic and Connectionist Learning Systems 1989
Douglas Fisher and Kathleen McKusick and Raymond J. Mooney and Jude W. Shavlik and Geoffrey Towell
Labs
Machine Learning