Categorization automata employing neuronal group selection with

Details Categorization automata employing neuronal group selection with Categorization automata employing neuronal group selection with

1989-10-10

1992-08-04

Fleming, Michael R.

Railway wheels and axles

Axle

Mine car

295 21, G06F 1500

Patent

active

051366878

ABSTRACT:
An apparatus capable of sensing the presence of objects in its environment, categorizing these objects without a prior description of the categories to be expected, and controlling robotic effector mechanisms to respond differentially to such objects according to their categories. Such responses include sorting objects, rejecting objects of certain types, and detecting novel or deviant objects. The invention includes a device called a "classification n-tuple" (of which a "classification couple" is a special case) capable of combining signals from two or more sensory modalities to arrive at the classification of the object.
The invention operates by simulating certain features of animal nervous system, including neurons with responses determined at each moment of time by inputs received along synaptic connections from sensory means or form other neurons. In this invention, neurons are arranged in "groups", which permits them to act cooperatively while still retaining characteristic individual responses. Groups in turn are arranged in "repertoires", which provide a totality of response specificities sufficient to respond to any of a range of possible input objects. Some of these repertoires are organized as "maps", such that groups responding to inputs that are similar along some dimensional (spatial or abstract) are close together in the repertoire, enabling the repertoire to respond correctly to novel objects that are similar to objects it has encountered previously. Maps in this invention are linked by connections, called "reentrant" connections, that enable the responses of one map to be reentered into the system as inputs to another map. Reentrant connections permit signals from different sensory modalities to be correlated in an ongoing fashion, and they are the basis for the operation of classification n-tuples.
The responses of the apparatus of this invention may be improved and optimized for a particular task through the operation of "neuronal group selection", a process which enhances the responses of those neuronal groups in the apparatus which were active in some time interval preceding the production of a useful output action. This process operates by modifying the strength of selected synaptic connections. The value of various output actions is determined, for the purpose of regulating selection, by means which are internal to the apparatus of this invention. Accordingly, the invention is capable of self-organization and learning, and does not require a predetermined specification of correct responses for all possible inputs.

REFERENCES:
patent: 4044243 (1977-08-01), Cooper et al.
patent: 4146924 (1979-03-01), Birk
patent: 4254474 (1981-03-01), Cooper
patent: 4305130 (1981-12-01), Kelley
patent: 4319331 (1982-03-01), Elbaum
patent: 4326259 (1982-04-01), Cooper
patent: 4739476 (1988-04-01), Fiduccia
patent: 4796199 (1989-01-01), Hammerstrom et al.
patent: 4852018 (1989-07-01), Grossberg et al.
patent: 4884216 (1989-11-01), Kuperstein
patent: 4918617 (1990-04-01), Hammerstrom et al.
Rumelhart, D. E. et al., Parallel Distributed Processing--Explorations in the Microstructure of Cognition, vol. 1, pp. 318-361, 1986.
Linsker, R., "Self-Organization in a Perceptual Network", IEEE Computer, Mar. 1988, pp. 105-117.
Josin, G., "Neural Network Heuristics", Byte, Oct. 1987, pp. 183-192.
Carpenter, G. et al., "The Art of Adaptive Pattern Recognition by a Self-Organizing Neural Network", IEEE Computer, Mar. 1988, pp. 77-88.
Edelman et al., "Selective Networks Capable of Representing Transformations, Limited Generalizations, and Associative Memory", Proc. Nat. Acad. Sci., Biol. Sci., 1982, vol. 79, No. 6, pp. 2091-2095.
Finkel et al, "Computer Simulations of Dynamic Functional Changes in the Topographic Maps of Adult Animals", 1989 IEEE Conf. on Neural Information Processing Sys.--Natural and Synthetic.
Zipser et al, "A Back-Propagation Programmed Network That Simulates Response Properties of a Subset of Posterior Parietal Neurons".
Hopfield, "Neural Networks and Physical System with Emergent Collective Capabilities".
Kuperstein, "Neural Model of Adaptive Hand-Eye Coordination for Single Postures".
Finkle et al, "Interaction of Synaptic Modification Rules with Populations of Neurons".
Reeke et al., "Selective Neural Networks and Their Implications for Recognition Automata", Internat. Journal of Supercomputer Applications, vol. 1, No. 1, Spring 1987.
Barto et al., "Gradaent Following Without Back-Propacation in Layered Networks" pp. 629-636.
Pearson et al., "Plasticity in the Organization of Adult Cerebral Cortical Maps", Jour. of Neuroscience, Dec. 1987, vol. 7, No. 12, pp. 4909-4923.
Hopfield et al., "Computing with Neural Circuits: A Model".
Reeke et al., "Selective Networks and Recognition Automata".

Affiliated with

Also associated with

Rating

Categorization automata employing neuronal group selection with does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Categorization automata employing neuronal group selection with , we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Categorization automata employing neuronal group selection with will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-785851