WO2004097733A3 - Neural networks - Google Patents

Neural networks Download PDF

Info

Publication number
WO2004097733A3
WO2004097733A3 PCT/GB2004/001847 GB2004001847W WO2004097733A3 WO 2004097733 A3 WO2004097733 A3 WO 2004097733A3 GB 2004001847 W GB2004001847 W GB 2004001847W WO 2004097733 A3 WO2004097733 A3 WO 2004097733A3
Authority
WO
WIPO (PCT)
Prior art keywords
neural networks
neuron
connections
neurons
evolve
Prior art date
Application number
PCT/GB2004/001847
Other languages
French (fr)
Other versions
WO2004097733A2 (en
Inventor
Jay Perrett
Daniel King
Original Assignee
Darwinian Neural Network Ind L
Jay Perrett
Daniel King
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Darwinian Neural Network Ind L, Jay Perrett, Daniel King filed Critical Darwinian Neural Network Ind L
Publication of WO2004097733A2 publication Critical patent/WO2004097733A2/en
Publication of WO2004097733A3 publication Critical patent/WO2004097733A3/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming

Abstract

There are disclosed methods of constructing artificial neural networks in a three dimensional model space. Data transfer properties of neuron to neuron connections depend upon the point of intersection of a connection with a spatially extensive boundary surface of the connected neuron. Axon connections directly interconnect neurons, and dendritic connections are formed between neurons and passing axons according to a proximity measure. An evolutionary algorithm is used to evolve a population of parameter genomes from which phenotype neural networks are constructed.
PCT/GB2004/001847 2003-04-30 2004-04-30 Neural networks WO2004097733A2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US46661403P 2003-04-30 2003-04-30
US60/466,614 2003-04-30

Publications (2)

Publication Number Publication Date
WO2004097733A2 WO2004097733A2 (en) 2004-11-11
WO2004097733A3 true WO2004097733A3 (en) 2005-12-29

Family

ID=33418404

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/GB2004/001847 WO2004097733A2 (en) 2003-04-30 2004-04-30 Neural networks

Country Status (1)

Country Link
WO (1) WO2004097733A2 (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007071070A1 (en) * 2005-12-23 2007-06-28 Universite De Sherbrooke Spatio-temporal pattern recognition using a spiking neural network and processing thereof on a portable and/or distributed computer
US9424513B2 (en) 2011-11-09 2016-08-23 Qualcomm Incorporated Methods and apparatus for neural component memory transfer of a referenced pattern by including neurons to output a pattern substantially the same as the referenced pattern
US9015091B2 (en) * 2011-11-09 2015-04-21 Qualcomm Incorporated Methods and apparatus for unsupervised neural replay, learning refinement, association and memory transfer: structural plasticity and structural constraint modeling
US9424511B2 (en) 2011-11-09 2016-08-23 Qualcomm Incorporated Methods and apparatus for unsupervised neural component replay by referencing a pattern in neuron outputs
US9443190B2 (en) 2011-11-09 2016-09-13 Qualcomm Incorporated Methods and apparatus for neural pattern sequence completion and neural pattern hierarchical replay by invoking replay of a referenced neural pattern
US9189729B2 (en) 2012-07-30 2015-11-17 International Business Machines Corporation Scalable neural hardware for the noisy-OR model of Bayesian networks
CN115359337B (en) * 2022-08-23 2023-04-18 四川大学 Searching method, system and application of pulse neural network for image recognition

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1990011568A1 (en) * 1989-03-28 1990-10-04 Honeywell Inc. Genetic synthesis of neural networks
US5485546A (en) * 1990-04-27 1996-01-16 Neurosciences Research Foundation, Inc. Discrimination and testing methods and apparatus employing adaptively changing network behavior based on spatial and heterocellular modification rules

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1990011568A1 (en) * 1989-03-28 1990-10-04 Honeywell Inc. Genetic synthesis of neural networks
US5485546A (en) * 1990-04-27 1996-01-16 Neurosciences Research Foundation, Inc. Discrimination and testing methods and apparatus employing adaptively changing network behavior based on spatial and heterocellular modification rules

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
ATSUMI M: "Artificial neural development for pulsed neural network design-a simulation experiment on animat's cognitive map genesis", COMBINATIONS OF EVOLUTIONARY COMPUTATION AND NEURAL NETWORKS, 2000 IEEE SYMPOSIUM ON SAN ANTONIO, TX, USA 11-13 MAY 2000, PISCATAWAY, NJ, USA,IEEE, US, 11 May 2000 (2000-05-11), pages 188 - 198, XP010525039, ISBN: 0-7803-6572-0 *
CANGELOSI A ET AL: "CELL DIVISION AND MIGRATION IN A GENOTYPE FOR NEURAL NETWORKS", NETWORK: COMPUTATION IN NEURAL SYSTEMS, IOP PUBLISHING, BRISTOL, GB, vol. 5, no. 4, 1 November 1994 (1994-11-01), pages 497 - 515, XP000489774, ISSN: 0954-898X *
GARIS DE H: "THE CAM-BRAIN MACHINE (CBM): REAL TIME EVOLUTION AND UPDATE OF A 75MILLION NEURON FPGA-BASED ARTIFICIAL BRAIN", JOURNAL OF VLSI SIGNAL PROCESSING SYSTEMS FOR SIGNAL, IMAGE, AND VIDEO TECHNOLOGY, KLUWER ACADEMIC PUBLISHERS, DORDRECHT, NL, vol. 24, no. 2/3, March 2000 (2000-03-01), pages 241 - 261, XP000908467, ISSN: 0922-5773 *

Also Published As

Publication number Publication date
WO2004097733A2 (en) 2004-11-11

Similar Documents

Publication Publication Date Title
Liu et al. Neuromorphic sensory systems
Zhang et al. A hybrid particle swarm optimization–back-propagation algorithm for feedforward neural network training
US6643627B2 (en) Dynamic synapse for signal processing in neural networks
Briscoe Linguistic evolution through language acquisition
Urzelai et al. Evolution of adaptive synapses: Robots with fast adaptive behavior in new environments
EP1901212A3 (en) Evolutionary neural network and method of generating an evolutionary neural network
TW201541372A (en) Artificial neural network and perceptron learning using spiking neurons
WO2003012738A1 (en) Optimal fitting parameter determining method and device, and optimal fitting parameter determining program
JP6327926B2 (en) Hierarchical neural network learning system and method
WO2004097733A3 (en) Neural networks
Marocco et al. Origins of communication in evolving robots
Joachimczak et al. Improving evolvability of morphologies and controllers of developmental soft-bodied robots with novelty search
Pontes-Filho et al. Towards the Neuroevolution of Low-level artificial general intelligence
Yoder et al. Evaluating topological models of neuromodulation in polyworld
Miras et al. Environmental regulation using plasticoding for the evolution of robots
AU2001260902A1 (en) Computer based system adapted to create a representation of the pumping action of a heart
JPH1091676A (en) Stabilized design method and recording medium recording stabilized design program
Lehman et al. Rewarding reactivity to evolve robust controllers without multiple trials or noise
Zahadat et al. Evolving reactive controller for a modular robot: Benefits of the property of state-switching in fractal gene regulatory networks
KR20220075025A (en) Neuromorphic computing device
Kulakov et al. Implementing artificial neural-networks in wireless sensor networks
Ferrari et al. Biologically realizable reward-modulated hebbian training for spiking neural networks
Joseph Theories of adaptive neural growth
Bowers et al. Embryological modelling of the evolution of neural architecture
Raudys On the universality of the single-layer perceptron model

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A2

Designated state(s): BW GH GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
122 Ep: pct application non-entry in european phase