Learning to control a dynamic physical system
AAAI'87 Proceedings of the sixth National conference on Artificial intelligence - Volume 2
Learning to control a dynamic physical system
AAAI'87 Proceedings of the sixth National conference on Artificial intelligence - Volume 2
Machine learning in building a collection of computer science course syllabi
TPDL'12 Proceedings of the Second international conference on Theory and Practice of Digital Libraries
Building a search engine for computer science course syllabi
Proceedings of the 13th ACM/IEEE-CS joint conference on Digital libraries
| Hi-index | 0.00 |
THE DIFFICULTIES OF LEARNING IN MULTILAYERED NETWORKS OF COMPUTATIONAL UNITS HAS LIMITED THE USE OF CONNECTIONIST SYSTEMS IN COMPLEX DOMAINS. THIS DISSERTATION ELUCIDATES THE ISSUES OF LEARNING IN A NETWORK''S HIDDEN UNITS, AND REVIEWS METHODS FOR ADDRESSING THESE ISSUES THAT HAVE BEEN DEVELOPED THROUGH THE YEARS. ISSUES OF LEARNING IN HIDDEN UNITS ARE SHOWN TO BE ANALOGOUS TO LEARNING ISSUES FOR MULTILAYER SYSTEMS EMPLOYING SYMBOLIC REPRSENTATIONS. COMPARISONS OF A NUMBER OF ALGORITHMS FOR LEARNING IN HIDDEN UNITS ARE MADE BY APPLYING THEM IN A CONSISTENT MANNER TO SEVERAL TASKS. RECENTLY DEVELOPED ALGORITHMS, INCLUDING RUMELHART, ET AL''S, ERROR BACK-PROPOGATIONS ALGORITHM AND BARTO, ET AL''S, REINFORCEMENT-LEARNING ALGORITHMS, LEARN THE SOLUTIONS TO THE TASKS MUCH MORE SUCCESSFULLY THAN METHODS OF THE PAST. A NOVEL ALGORITHM IS EXAMINED THAT COMBINES ASPECTS OF REINFORCEMENT LEARNING AND A DATA-DIRECTED SEARCH FOR USEFUL WEIGHTS, AND IS SHOWN TO OUT PERFORM REINFORMCEMENT-LEARNING ALGORITHMS. A CONNECTIONIST FRAMEWORK FOR THE LEARNING OF STRATEGIES IS DESCRIBED WHICH COMBINES THE ERROR BACK-PROPOGATION ALGORITHM FOR LEARNING IN HIDDEN UNITS WITH SUTTON''S AHC ALGORITHM TO LEARN EVALUATION FUNCTIONS AND WITH A REINFORCEMENT-LEARNING ALGORITHM TO LEARN SEARCH HEURISTICS. THE GENERAL- ITY OF THIS HYBRID SYSTEM IS DEMONSTRATED THROUGH SUCCESSFUL APPLICATIONS