Cooper Leon N. (Providence RI) Elbaum Charles (Providence RI)
출원인 / 주소
Nestor Associates (New York NY 02)
인용정보
피인용 횟수 :
92인용 특허 :
0
초록▼
An adaptive information processing system includes a module, called a Nestor module, having a plurality (N) of input terminals 1, 2 . . . , j . . . , N, adapted to receive N input signals s1, s2 . . . , sj . . . , SN, respectively, and a plurality (n) of output terminals 1, 2 . . . , i . . . , n, ad
An adaptive information processing system includes a module, called a Nestor module, having a plurality (N) of input terminals 1, 2 . . . , j . . . , N, adapted to receive N input signals s1, s2 . . . , sj . . . , SN, respectively, and a plurality (n) of output terminals 1, 2 . . . , i . . . , n, adapted to present n output responses r1, r2 . . . , ri . . . , rn, respectively. A plurality of junction elements, called mnemonders, couple various ones (or a multiplicity) of the input terminals with various ones (or a multiplicity) of the output terminals. These mnemonders provide a transfer of information from an input terminal j to an output terminal i in dependence upon the signal sj appearing at the input terminal j and upon the mnemonder transfer function Aij. Means are provided for modifying the transfer function Aij of the mnemonders in dependence upon the product of at least one of the input signals and one of the output responses of the Nestor module. In a preferred embodiment of the invention, the modification to the transfer function of each mnemonder takes the form: n dAij =hj ri =hj SAik sk k=1 WHERE h
대표청구항▼
An information processing module comprising, in combination: a. a plurality (N) of input terminals 1, 2 . . . , j . . . , N adapted to receive N input signals s1, s2 . . . , sj . . . , sN, respectively; b. a plurality (n) of output terminals 1, 2 . . . , i . . . , n adapted to present n output respo
An information processing module comprising, in combination: a. a plurality (N) of input terminals 1, 2 . . . , j . . . , N adapted to receive N input signals s1, s2 . . . , sj . . . , sN, respectively; b. a plurality (n) of output terminals 1, 2 . . . , i . . . , n adapted to present n output responses r1, r2 . . . , ri . . . , rn, respectively; c. a plurality of junction elements, called mnemonders, each mnemonder coupling one of said input terminals (input j) with one of said output terminals (output i) and providing a transfer of information from input j to output i in dependence upon the signal sj appearing at the input j and upon the mnemonder transfer function Aij; and d. means for modifying the transfer function Aij of at least one of said mnemonders, when in a learning mode, in dependence upon the product of at least one of said input signals and one of said output responses; whereby modifications to the transfer functions of the mnemonders, when in a learning mode, take the form: eij =f (s1, s2 . . . , sj . . . , sN ; r1, r2 . . . , ri . . . , rn).
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허를 인용한 특허 (92)
Wood Laurence F. (Medway MA), Accelerating learning in neural networks.
Holland John H. (3800 W. Huron River Dr. Ann Arbor MI 48103) Burks Arthur W. (3445 Vintage Valley Rd. Ann Arbor MI 48105), Adaptive computing system capable of learning and discovery.
Andes David K. (Ridgecrest CA) Licklider Robert A. (Ridgecrest CA) Witcher Donald H. (Ridgecrest CA) Swenson Richard M. (Ridgecrest CA), Artificial neural network implementation.
Marko Kenneth A. (Ann Arbor MI) James John V. (Walled Lake MI) Dosdall James M. (Grosse Ile MI), Diagnostic system using pattern recognition for electronic automotive control systems.
Paganini Bruno J. (Centerville OH) Advani Jeram G. (Miami FL) Whitely Robert M. (Dayton OH) Hale William J. (Dayton OH), Identity verification apparatus and method.
Grossberg Stephen (Newton Highlands MA) Kuperstein Michael (Brookline MA), Massively parellel real-time network architectures for robots capable of self-calibrating their operating parameters thr.
Lewis,Michael; King,Frank; Arnold,Thomas; Wright,William; Pettit,John, Method and apparatus for evaluating fraud risk in an electronic commerce transaction.
van Heerden Pieter J. (18217 145th Court N. E. Woodinville WA 98072) Marks ; II Robert J. (1131 - 199th St. ; S. W. Lynwood WA 98036) Oh ; Seho (4747 30th Ave. ; N. E. #K173 Seattle WA 98105), Method and apparatus for identifying that one of a set of past or historical events best correlated with a current or re.
Meng Wan-Yu,TWX ; Chang Cheng-Kai,TWX ; Chang Hwai-Tsu,TWX ; Hsu Fang-Ru,TWX ; Lee Ming-Rong,TWX, Method and apparatus for processing data in a neural network.
Hoffberg, Steven M; Hoffberg-Borghesani, Linda I, Mobile system, a method of operating mobile system and a non-transitory computer readable medium for a programmable control of a mobile system.
Reilly Douglas L. (Providence RI) Scofield Christopher L. (Barrington RI) Cooper Leon N. (Providence RI) Elbaum Charles (Providence RI), Parallel, multi-unit, adaptive pattern classification system using inter-unit correlations and an intra-unit class separ.
Smith Allen R. (Shelton CT) Tan Chuan-Chieh (Orange CT) Slack Thomas B. (Oxford CT) Denenberg Jeffrey N. (Trumbull CT), Probabilistic learning element.
Tan Chuan-Chieh (Orange CT) Slack Thomas B. (Oxford CT) Denenberg Jeffrey N. (Trumbull CT), Probabilistic learning element employing context drive searching.
Cooper Leon N. (Providence RI) Elbaum Charles (Providence RI) Reilly Douglas L. (Providence RI), Self organizing general pattern class separator and identifier.
Buckley Bruce S. (7067 Via Blanca San Jose CA 95139), Self-organizing circuits for automatic pattern recognition and the like and systems embodying the same.
Carpenter Gail A. (Newton Highlands MA) Grossberg Stephen (Newton Highlands MA), System for self-organization of stable category recognition codes for analog input patterns.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.