Accession Number : ADA264831


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


Descriptive Note : Final technical rept. 1 Oct 89-31 Dec 92,


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/a264831.pdf


Report Date : Mar 1993


Pagination or Media Count : 27


Abstract : During the DARPA ANNT Program contract, 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 , *COMPUTER ARCHITECTURE , *PATTERN RECOGNITION , SIGNAL PROCESSING , INPUT , ADAPTIVE CONTROL SYSTEMS , PREDICTIONS , REAL TIME , LEARNING MACHINES , DEPTH , COMPUTER VISION , ACOUSTICS , RECOGNITION , ACOUSTIC SIGNALS , PATTERNS , SIGNALS , SCHEDULING , MEMORY DEVICES , TIME , PREPROCESSING , PERCEPTION , MOTORS , LEARNING , HEAD(ANATOMY) , TARGETS , MOTION , PROCESSING , NETWORKS , CONTRACTS , NEURAL NETS , CONTROL


Subject Categories : Computer Hardware
      Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE