Accession Number : ADA255433


Title :   Development of Neural Network Architectures for Self-Organizing Pattern Recognition and Robotics


Descriptive Note : Annual technical rept. no. 2, 15 Dec 1990-14 Feb 1992


Corporate Author : BOSTON UNIV MA CENTER FOR ADAPTIVE SYSTEMS


Personal Author(s) : Carpenter, Gail A ; Grossberg, Stephen


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a255433.pdf


Report Date : Jul 1992


Pagination or Media Count : 18


Abstract : During the second year of the DARPA ANNT Program contact, new neural network architectures were developed to carry out autonomous real-time preprocessing, segmentation, recognition, timing, and control of both spatial and temporal inputs. These architectures contribute to: (1) preprocessing of visual form and motion signals; (2) preprocessing of acoustic signals; (3) adaptive pattern recognition and categorization in an unsupervised learning context; (4) adaptive pattern recognition and prediction in a supervised learning context; (5) processing of temporal patterns using working memory networks, with applications to 3-D object recognition; (6) adaptive timing for task scheduling; (7) adaptive sensory-motor control using head-centered spatial representations of 3-D target position.


Descriptors :   *ROBOTICS , *NEURAL NETS , *COMPUTER ARCHITECTURE , *PATTERN RECOGNITION , SIGNAL PROCESSING , PREDICTIONS , REAL TIME , TARGETS , SCHEDULING , PATTERNS , SELF ORGANIZING SYSTEMS , PREPROCESSING , MOTORS , LEARNING , HEAD(ANATOMY) , ARCHITECTURE , ACOUSTICS , RECOGNITION , ACOUSTIC SIGNALS , SIGNALS , TIME , MOTION , PROCESSING , NETWORKS , INPUT , CONTROL


Subject Categories : Computer Systems
      Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE