[논문]Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition

Kasabov, N.; Dhoble, K.; Nuntalid, N.; Indiveri, G.

doi:10.1016/j.neunet.2012.11.014

Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition 원문보기

Neural networks : the official journal of the International Neural Network Society, v.41, 2013년, pp.188 - 201

Kasabov, N. , Dhoble, K. , Nuntalid, N. , Indiveri, G.

Abstract ▼ AI-Helper

On-line learning and recognition of spatio- and spectro-temporal data (SSTD) is a very challenging task and an important one for the future development of autonomous machine learning systems with broad applications. Models based on spiking neural networks (SNN) have already proved their potential in capturing spatial and temporal data. One class of them, the evolving SNN (eSNN), uses a one-pass rank-order learning mechanism and a strategy to evolve a new spiking neuron and new connections to learn new patterns from incoming data. So far these networks have been mainly used for fast image and speech frame-based recognition. Alternative spike-time learning methods, such as Spike-Timing Dependent Plasticity (STDP) and its variant Spike Driven Synaptic Plasticity (SDSP), can also be used to learn spatio-temporal representations, but they usually require many iterations in an unsupervised or semi-supervised mode of learning. This paper introduces a new class of eSNN, dynamic eSNN, that utilise both rank-order learning and dynamic synapses to learn SSTD in a fast, on-line mode. The paper also introduces a new model called deSNN, that utilises rank-order learning and SDSP spike-time learning in unsupervised, supervised, or semi-supervised modes. The SDSP learning is used to evolve dynamically the network changing connection weights that capture spatio-temporal spike data clusters both during training and during recall. The new deSNN model is first illustrated on simple examples and then applied on two case study applications: (1) moving object recognition using address-event representation (AER) with data collected using a silicon retina device; (2) EEG SSTD recognition for brain-computer interfaces. The deSNN models resulted in a superior performance in terms of accuracy and speed when compared with other SNN models that use either rank-order or STDP learning. The reason is that the deSNN makes use of both the information contained in the order of the first input spikes (which information is explicitly present in input data streams and would be crucial to consider in some tasks) and of the information contained in the timing of the following spikes that is learned by the dynamic synapses as a whole spatio-temporal pattern.

주제어

참고문헌 (77)

Arthur 2012 Proc. IJCNN 2012 Building block of a programmable neuromorphic substrate: a digital neurosynaptic core
Neurology Barker-Collo 75 18 1608 2010 10.1212/WNL.0b013e3181fb44c8 Auckland stroke outcomes study

상세보기
Soft Computing Belatreche 11 3 239 2006 10.1007/s00500-006-0065-7 Advances in design and application of spiking neural networks

상세보기
IEEE Transactions on Autonomous Mental Development Bellas 2 340 2010 10.1109/TAMD.2010.2086453 MDB: artificial evolution in a cognitive architecture for real robots

상세보기
Benuskova 2007 Computational neurogenetic modelling
Bichler 859 2011 Proc. IJCNN 2011 Unsupervised features extraction from asynchronous silicon retina spike-timing-dependent plasticity
Natural Computing Bohte 3 2004 10.1023/B:NACO.0000027755.02868.60 The evidence for neural information processing with precise spike-times: a survey

상세보기
Neural Computation Brader 19 11 2881 2007 10.1162/neco.2007.19.11.2881 Learning real-world stimuli in a neural network with spike-driven synaptic dynamics

상세보기
Journal of Computational Neuroscience Brette 23 349 2007 10.1007/s10827-007-0038-6 Simulation of networks of spiking neurons: a review of tools and strategies

상세보기
IEEE Transactions on Evolutionary Computation Defoin-Platel 13 6 1218 2009 10.1109/TEVC.2008.2003010 Quantum-inspired evolutionary algorithm: a multi-model EDA

상세보기
Delbruck, T. (2007). jAER open source project. http://jaer.wiki.sourceforge.net.
Dhoble 554 2012 Proc. WCCI 2012 On-line spatiotemporal pattern recognition with evolving spiking neural networks utilising address event representation, rank oder- and temporal spike learning
Ferreira vol. 6112 287 2010 ICIAR 2010 Advances in EEG-based biometry
Neural Computation Fusi 12 10 2227 2000 10.1162/089976600300014917 Spike-driven synaptic plasticity: theory, simulation, VLSI implementation

상세보기
Physical Review Gerstner 51 738 1995 Time structure of the activity of neural network models
Neural Computation Guyonneau 17 4 859 2005 10.1162/0899766053429390 Neurons tune to the earliest spikes through STDP

상세보기
Hebb 1949 The organization of behavior
Journal of Physiology Hodgkin 117 500 1952 10.1113/jphysiol.1952.sp004764 A quantitative description of membrane current and its application to conduction and excitation in nerve

상세보기
Cognitive Computation Indiveri 1 2 119 2009 10.1007/s12559-008-9003-6 Artificial cognitive systems: from VLSI networks of spiking neurons to neuromorphic cognition

상세보기
Frontiers in Neuroscience Indiveri 5 118 2011 10.3389/fnins.2011.00118 Frontiers in neuromorphic engineering

상세보기
Frontiers in Neuroscience Indiveri 5 1 2011 10.3389/fnins.2011.00073 Neuromorphic silicon neuron circuits

상세보기
10.1109/ISCAS.2010.5536980 Indiveri, G., Stefanini, F., & Chicca, E. (2010). Spike-based learning with a generalized integrate and fire silicon neuron. In 2010 IEEE int. symp. circuits and syst., ISCAS 2010 (pp. 1951-1954). Paris, May 30-June 02.
Neural Networks Isa 22 9 1201 2009 10.1016/j.neunet.2009.10.003 Recent advances in brain-machine interfaces

상세보기
IEEE Transactions on Neural Networks Izhikevich 15 5 1063 2004 10.1109/TNN.2004.832719 Which model to use for cortical spiking neurons?

상세보기
Neural Computation Izhikevich 18 245 2006 10.1162/089976606775093882 Polychronization: computation with spikes

상세보기
Computing in Science & Engineering Jin 12 5 91 2010 10.1109/MCSE.2010.112 Modelling spiking neural networks on SpiNNaker

상세보기
IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) Kasabov 31 6 902 2001 10.1109/3477.969494 Evolving fuzzy neural networks for on-line supervised/unsupervised, knowledge-based learning

상세보기
Kasabov 2002 Evolving connectionist systems: methods and applications in bioinformatics, brain study and intelligent machines
Kasabov 2007 Evolving connectionist systems - The knowledge engineering approach
Neural Networks Kasabov 23 1 16 2010 10.1016/j.neunet.2009.08.010 To spike or not to spike: a probabilistic spiking neuron model

상세보기
Kasabov vol. 7311 234 2012 IEEE WCCI 2012 Evolving spiking neural networks and neurogenetic systems for spatio- and spectro-temporal data modelling and pattern recognition
Kasabov vol. 7477 225 2012 ANNPR NeuCube EvoSpike architecture for spatio-temporal modelling and pattern recognition of brain signals
2013 The springer handbook of bio- and neuroinformatics
Kasabov 446 2005 IJCNN 2005 conf. proc. vol. 1 A computational neurogenetic model of a spiking neuron
International Journal of Functional Informatics and Personalised Medicine Kasabov 3 3 236 2010 10.1504/IJFIPM.2010.039123 Integrated optimisation method for personalised modelling and case study applications

상세보기
IEEE Transactions on Autonomous Mental Development Kasabov 3 4 300 2011 10.1109/TAMD.2011.2159839 Probabilistic computational neurogenetic framework: from modelling cognitive systems to alzheimer’s disease

상세보기
IEEE Transactions on Fuzzy Systems Kasabov 10 144 2002 10.1109/91.995117 DENFIS: dynamic, evolving neural-fuzzy inference systems and its application for time-series prediction

상세보기
Kistler 2002 Spiking neuron models-single neurons, populations, plasticity
EURASIP Journal on Applied Signal Processing Lalor 2005 3156 2005 10.1155/ASP.2005.3156 Steady-state vep-based brain-computer interface control in an immersive 3D gaming environment

상세보기
Research in Microelectronics and Electronics Lichtsteiner 2 202 2005 A 64×64 AER logarithmic temporal derivative silicon retina
Neural Networks Maass 15 2 155 2002 10.1016/S0893-6080(01)00144-7 Synapses as dynamic memory buffers

상세보기
Neural Computation Maass 14 11 2531 2002 10.1162/089976602760407955 Real-time computing without stable states: a new framework for neural computation based on perturbations

상세보기
Neural Computation Maass 12 8 1743 2000 10.1162/089976600300015123 Neural systems as nonlinear filters

상세보기
Maass 321 1999 Pulsed neural networks Computing and learning with dynamic synapses
PLoS ONE Masquelier 3 1 e1377 2008 10.1371/journal.pone.0001377 Spike timing dependent plasticity finds the start of repeating patterns in continuous spike trains

상세보기
Neural Computation Masquelier 21 5 1259 2009 10.1162/neco.2008.06-08-804 Competitive STDP-based spike pattern learning

상세보기
Neural Computing & Applications Mehrtash 12 33 2003 10.1007/s00521-030-0371-2 Image pre-processing with dynamic synapses

상세보기
IEEE Transactions on Biomedical Circuits and Systems Mitra 3 1 32 2009 10.1109/TBCAS.2008.2005781 Real-time classification of complex patterns using spike-based learning in neuromorphic VLSI

상세보기
10.1109/BioCAS.2011.6107781 Moradi, S., & Indiveri, G. (2011). A VLSI network of spiking neurons with an asynchronous static random access memory. In Biomedical circuits and systems conference BIOCAS 2011.
Biological Cybernetics Morrison 98 459 2008 10.1007/s00422-008-0233-1 Phenomenological models of synaptic plasticity based on spike timing

상세보기
10.1109/IJCNN.2001.938853 Namarvar, H., Liaw, J.-S., & Berger, T. (2001). A new dynamic synapse neural network for speech recognition. In Proc. IJCNN’01. int. joint conf. on neural networks, 2001.
Theoretical Computer Science-Natural Computing Natschlager 287 1 251 2002 10.1016/S0304-3975(02)00099-3 Spiking neurons and the induction of finite state machines

상세보기
Clinical Neurophysiology Neuper 114 3 399 2003 10.1016/S1388-2457(02)00387-5 Clinical application of an EEG -based brain-computer interface: a case study in a patient with severe motor impairment

상세보기
Nuntalid vol. 7062 451 2011 Proc. 18th int. conf. on neural information processing, ICONIP, 2011, Shanghai, China EEG classification with BSA spike encoding algorithm and evolving probabilistic spiking neural network
Australian Journal of Intelligent Information Processing Systems Nuzly 11 1 2010 Probabilistic evolving spiking neural network optimization using dynamic quantum inspired particle swarm optimization
Neural Networks Schliebs 22 623 2009 10.1016/j.neunet.2009.06.038 Integrated feature and parameter optimization for evolving spiking neural networks: exploring heterogeneous probabilistic models

상세보기
Schliebs vol. 7552 604 2012 ICANN 2012 Constructing robust liquid state machines to process highly variable data streams
Schliebs vol. 7063 160 2011 Proc. 18th int. conf. neural information processing A reservoir-based evolving spiking neural network for on-line spatio-temporal pattern learning and recognition, Neural Information Processing
Schliebs 2012 Evolving spiking neural networks: a survey, evolving systems
International Journal of Neural Systems Schliebs 20 6 481 2010 10.1142/S0129065710002565 On the probabilistic optimization of spiking neural networks

상세보기
Schrauwen 2825 2003 2003 Proc. int. joint conf. on neural networks. Vol. 4 BSA-a fast and accurate spike train encoding scheme
International Journal of Neural Systems Soltic 20 6 437 2010 10.1142/S012906571000253X Knowledge extraction from evolving spiking neural networks with rank order population coding

상세보기
Sona vol. 4669 869 2007 ICANN 2007 Inferring cognition from fMRI brain images
Nature Neuroscience Song 3 919 2000 10.1038/78829 Competitive Hebbian learning through spike-timing-dependent synaptic plasticity

상세보기
IEEE Transactions on Robotics Tanaka 21 4 762 2005 10.1109/TRO.2004.842350 Electroencephalogram-based control of an electric wheelchair

상세보기
Neuron Thorpe 62 2 168 2009 10.1016/j.neuron.2009.04.012 The speed of categorization in the human visual system

상세보기
Lecture Notes in Computer Science Thorpe vol. 7583 516 2012 10.1007/978-3-642-33863-2_53 Spike-based image processing: can we reproduce biological vision in hardware

상세보기
10.1109/ISCAS.2010.5537898 Thorpe, S.J., Brilhault, A., & Perez-Carrasco, J.A. (2010). Suggestions for a biologically inspired spiking retina using order-based coding. In IEEE international symposium on circuits and syst. (pp. 265-268).
Computational Neuroscience Thorpe 13 113 1998 10.1007/978-1-4615-4831-7_19 Rank order coding
Neurocomputing Thorpe 58-60 857 2004 10.1016/j.neucom.2004.01.138 SpikeNet: real-time visual processing with one spike per neuron

상세보기
Neural Computation Tsodyks 10 4 821 1998 10.1162/089976698300017502 Neural networks with dynamic synapses

상세보기
10.1109/ISCAS.2005.1465560 van Schaik, A., & Shih-Chii Liu, L. (2005). AER EAR: a matched silicon cochlea pair with address event representation interface. In Proc. of ISCAS-IEEE int. symp. on circuits and systems, Vol. 5 (pp. 4213-4216). May.
Neural Networks Verstraeten 20 3 391 2007 10.1016/j.neunet.2007.04.003 An experimental unification of reservoir computing methods

상세보기
Wang 2012 Proc. ICONIP 2012 Mobile robots’ target-reaching controller based on spiking neural networks
IEEE Transactions on Systems, Man, and Cybernetics Part C: Applications and Reviews Watts 39 3 253 2009 10.1109/TSMCC.2008.2012254 A decade of Kasabov’s evolving connectionist systems: a review

상세보기
IEEE Transactions on Rehabilitation Engineering Wolpaw 8 2 222 2000 10.1109/86.847823 Brain-computer interface research at the wadsworth center

상세보기
Neural Networks Wysoski 23 7 819 2010 10.1016/j.neunet.2010.04.009 Evolving spiking neural networks for audiovisual information processing

상세보기

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증

Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition 원문보기

Abstract ▼ AI-Helper

주제어

참고문헌 (77)

이 논문을 인용한 문헌

관련 콘텐츠

원문 보기

원문 URL 링크

오픈액세스(OA) 유형

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트