Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Robust reasoning: integrating rule-based and similarity-based reasoning
Artificial Intelligence
Extracting rules from neural networks by pruning and hidden-unit splitting
Neural Computation
Knowledge-based neurocomputing
Knowledge-based neurocomputing
Symbolic knowledge extraction from trained neural networks: a sound approach
Artificial Intelligence
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Neural-Symbolic Learning System: Foundations and Applications
Neural-Symbolic Learning System: Foundations and Applications
Approximating the Semantics of Logic Programs by Recurrent Neural Networks
Applied Intelligence
Three problems in computer science
Journal of the ACM (JACM)
Logic and Learning
Extracting Provably Correct Rules from Artificial Neural Networks
Extracting Provably Correct Rules from Artificial Neural Networks
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Connectionist modal logic: Representing modalities in neural networks
Theoretical Computer Science
| Hi-index | 0.00 |
Seventeen years ago, John McCarthy wrote the note Epistemological challenges for connectionism as a response to Paul Smolensky's paper On the proper treatment of connectionism. I will discuss the extent to which the four key challenges put forward by McCarthy have been solved, and what are the new challenges ahead. I argue that there are fewer epistemological challenges for connectionism, but progress has been slow. Nevertheless, there is now strong indication that neural-symbolic integration can provide effective systems of expressive reasoning and robust learning due to the recent developments in the field.