Evolutionary neural network and method of generating an evolutionary neural network
IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0847537
(2007-08-30)
|
등록번호 |
US7882052
(2011-01-18)
|
발명자
/ 주소 |
- Szathmary, Eors
- Szatmary, Zoltan
- Ittzes, Peter
- Szamado, Szabolcs
|
대리인 / 주소 |
|
인용정보 |
피인용 횟수 :
0 인용 특허 :
6 |
초록
▼
An evolutionary neural network and a method of generating such a neural network is disclosed. The evolutionary neural network comprises an input set consisting of at least one input neuron, said input neurons being adapted for receiving an input signal form an external system, an output set consisti
An evolutionary neural network and a method of generating such a neural network is disclosed. The evolutionary neural network comprises an input set consisting of at least one input neuron, said input neurons being adapted for receiving an input signal form an external system, an output set consisting of at least one output neuron, said output neurons being adapted for producing an output signal for said external system, an internal network composed of a plurality of internal neurons, each internal neuron being adapted for processing a signal received from at least one of said input neurons or other internal neurons and producing a signal for at least one of said output neurons or other internal neurons, and a plurality of synapses constituting connections between said neurons, each of said synapses having a value of strength that can be adjusted by a learning process. Each of said neurons is assigned to a neuron class, the parameter values of which are defined by the genotype of the neural network, and each of said synapses are assigned to a respective synapse class, the parameter values of which are also defined by said genotype of the neural network. At reproduction, the genotype of any new neural network is subject to genetic operations. The evolutionary neural network is associated with a neural space, said neural space comprising a plurality of neural layers. Each neuron is associated with at least one neural layer and described by a set of topographical parameters with respect to said neural space. At least one of said topographical parameters of at least the internal neurons is encoded in the genotype of the evolutionary neural network in a statistical form.
대표청구항
▼
The invention claimed is: 1. An evolutionary neural network, comprising:an input set consisting of at least one input neuron, said input neurons being adapted for receiving an input signal form an external system;an output set consisting of at least one output neuron, said output neurons being adapt
The invention claimed is: 1. An evolutionary neural network, comprising:an input set consisting of at least one input neuron, said input neurons being adapted for receiving an input signal form an external system;an output set consisting of at least one output neuron, said output neurons being adapted for producing an output signal for said external system;an internal network composed of a plurality of internal neurons, each internal neuron being adapted for processing a signal received from at least one of said input neurons or other internal neurons and producing a signal for at least one of said output neurons or other internal neurons; anda plurality of synapses constituting connections between said neurons, each of said synapses having a value of strength that can be adjusted by a learning process,wherein each of said neurons is assigned to a neuron class, the parameter values of which are defined by the genotype of the evolutionary neural network,wherein each of said synapses are assigned to a respective synapse class, the parameter values of which are also defined by said genotype of the evolutionary neural network,wherein, at reproduction, the genotype of any new neural network is subject to genetic operations,wherein the evolutionary neural network is associated with a neural space, said neural space comprising a plurality of neural layers,wherein each neuron is associated with at least one neural layer and described by a set of topographical parameters with respect to said neural space, andwherein at least one of said topographical parameters of at least the internal neurons is encoded in the genotype of the evolutionary neural network in a statistical form.
이 특허에 인용된 특허 (6)
-
Bloom, Burton H.; Bhagwat, Chitra Balwant; Stengard, Peter, Automated model building and evaluation for data mining system.
-
Fogel David B. (San Diego CA) Fogel Lawrence J. (La Jolla CA), Method and apparatus for training a neural network using evolutionary programming.
-
Kato Hideki,JPX, Neural network for providing hints to problem solving apparatus using tree search method.
-
Heider Juergen (Munich DEX) Gosslar Achim (Munich DEX), Pinch-sealed high pressure discharge lamp, and method of its manufacture.
-
Kato Hideki,JPX, Problem solving apparatus having learning function.
-
Jin,Yaochu; Sendhoff,Bernhard, Reduction of fitness evaluations using clustering techniques and neural network ensembles.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.