Learning in structured connectionist networks. Technical report

Technical Report · Fri Apr 01 04:00:00 EST 1988

OSTI ID:5754956

Fanty, M A

Connectionist networks compute in a manner analogous to real neural networks. This work focuses on computing and especially learning in structured connectionist networks -- those which emphasize problem-specific connection patterns as well as adaptive weight change rules. A connectionist chart parser was implemented which parses limited-length strings for context-free grammars in a constant number of parallel-computations steps. The parser was extended to disambiguate and complete near-miss parses, as well as learn new production in certain limited situations. While the parser works well, the structure is too rigid and learning too difficult for cognitive modeling. Two algorithms for learning simple, feature-based concept descriptions were also implemented. The first recruits hidden units representing pairs of features. The performance of this network is good when the definition involve pairs of input features, but attempts to build hierarchies of pair units for longer definitions were not successful. The second algorithm is an enhancement of an existing technique, competitive learning, adding feedback from concept units to guide the partitioning of inputs into classes. This technique is more successful and is used as a component in a network which is capable of learning descriptions of structured objects.

• Research Organization: Rochester Univ., NY (USA). Dept. of Computer Science
• OSTI ID: 5754956
• Report Number(s): AD-A-206852/6/XAB; TR-252
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
990210* -- Supercomputers-- (1987-1989)
ALGORITHMS
ARTIFICIAL INTELLIGENCE
COMPUTER NETWORKS
DOCUMENT TYPES
FUNCTIONS
MATHEMATICAL LOGIC
PARALLEL PROCESSING
PATTERN RECOGNITION
PROGRAMMING
PROGRESS REPORT
WEIGHTING FUNCTIONS