5,907 Hits in 3.6 sec

A Cognitive Architecture Based on a Learning Classifier System with Spiking Classifiers [article]

David Howard, Larry Bull, Pier-Luca Lanzi
2015 arXiv   pre-print
Learning Classifier Systems (LCS) are population-based reinforcement learners that were originally designed to model various cognitive phenomena.  ...  This paper presents an explicitly cognitive LCS by using spiking neural networks as classifiers, providing each classifier with a measure of temporal dynamism.  ...  Conclusions and Outlook In this article we have presented a cognitive architecture based on temporal reinforcement learning and spiking networks.  ... 
arXiv:1508.07700v1 fatcat:7loktdgxybe3bmc7sgnpcvjvzm

A Cognitive Architecture Based on a Learning Classifier System with Spiking Classifiers

David Howard, Larry Bull, Pier-Luca Lanzi
2015 Neural Processing Letters  
A cognitive architecture based on a learning classifier system with spiking classifiers.  ...  Conclusions and Outlook In this article we have presented a cognitive architecture based on temporal reinforcement learning and spiking networks.  ...  This approach aims to move towards a more powerful, plausible cognitive architecture based on the rich intrinsic neural dynamics of spiking classifiers.  ... 
doi:10.1007/s11063-015-9451-4 fatcat:7jfdklzyjzettknqrpvci4erie

Parkinson's Disease Classification using Various Advanced Neural Network Classifiers

2019 International journal of recent technology and engineering  
This paper proposes the application of Online Meta-neuron Based Learning Algorithm (OMLA), Self adaptive Resource Allocation Network (SRAN) and Projection Based Learning Meta-cognitive Radial Basis Functional  ...  Online Meta-neuron based Learning Algorithm (OMLA) is a newly evolved network applied for Parkinson's disease classification.  ...  Architecture of OMLA a T d is Time based delete threshold, t MC is Spike time of different class neuron with minimum latency, T m is Time based marginal threshold and α d is Delete threshold.  ... 
doi:10.35940/ijrte.d7924.118419 fatcat:hxfecatwsjemrbgmcyavt3hsk4

Spiking neural network methodology for modelling, classification and understanding of EEG spatio-temporal data measuring cognitive processes

Nikola Kasabov, Elisa Capecci
2015 Information Sciences  
The proposed methodology is based on a recently proposed novel spiking neural network architecture, called NeuCube as a general framework for spatio-temporal brain data modelling.  ...  The methodology is demonstrated on benchmark cognitive EEG data.  ...  Acknowledgements The work on NeuCube SNN started in 2012 and was initially supported by the EU FP7 Marie Curie project EvoSpike PIIF-GA-2010-272006, hosted by the Institute for Neuroinformatics at ETH/  ... 
doi:10.1016/j.ins.2014.06.028 fatcat:p6lfzer3yzcipdedjs7dbledjy

Lightweight Building of an Electroencephalogram-Based Emotion Detection System

Abeer Al-Nafjan, Khulud Alharthi, Heba Kurdi
2020 Brain Sciences  
In this study, we investigated the feasibility of using a spiking neural network to build an emotion detection system from a smaller version of the DEAP dataset with no involvement of feature extraction  ...  The results showed that by using a NeuCube-based spiking neural network, we could detect the valence emotion level using only 60 EEG samples with 84.62% accuracy, which is a comparable accuracy to that  ...  Acknowledgments: This research project was supported by a grant from the Research Center of the Female Scientific and Medical Colleges, Deanship of Scientific Research, King Saud University.  ... 
doi:10.3390/brainsci10110781 pmid:33114646 fatcat:wcyrlfgnc5gfdavjfyftapzpnm


Ning Xiong, Defu Zhang, Libo Wang
2016 Neural Processing Letters  
systems with stronger learning capability.  ...  Nowadays, the focus in that area covers a wide spectrum in relation with machine learning, artificial intelligence, cognitive science, as well as computational neuroscience.  ...  The paper "A cognitive architecture based on a learning classifier system with spiking classifiers" by Howard, Bull, and Lanzi aims to build learning classifier system (LCS) as a cognitive architecture  ... 
doi:10.1007/s11063-016-9533-y fatcat:63jnzu5ssrd2ditv2t3h2m35r4

Artificial Cognitive Systems: From VLSI Networks of Spiking Neurons to Neuromorphic Cognition

Giacomo Indiveri, Elisabetta Chicca, Rodney J. Douglas
2009 Cognitive Computation  
Specifically, we show how VLSI networks of spiking neurons with spike-based plasticity mechanisms and soft winner-take-all architectures represent important building blocks useful for implementing artificial  ...  The challenge is to bridge the gap from reactive systems to ones that are cognitive in quality.  ...  Spike-Based Learning An additional feature that is crucial for implementing cognitive systems with networks of spiking neurons is spike-based plasticity.  ... 
doi:10.1007/s12559-008-9003-6 fatcat:gzrod52nxzgqzdifiedgqffwoi

Energy Efficient RRAM Spiking Neural Network for Real Time Classification

Yu Wang, Tianqi Tang, Lixue Xia, Boxun Li, Peng Gu, Huazhong Yang, Hai Li, Yuan Xie
2015 Proceedings of the 25th edition on Great Lakes Symposium on VLSI - GLSVLSI '15  
The spiking neural network (SNN), which encodes and processes information with bionic spikes, is an emerging neuromorphic model with great potential to drastically promote the performance and efficiency  ...  Our RRAM SNN systems for these two training algorithms show good power efficiency and recognition performance on realtime classification tasks, such as the MNIST digit recognition.  ...  (2) Design on-line learning RRAM based SNN system.  ... 
doi:10.1145/2742060.2743756 dblp:conf/glvlsi/WangTXLGYL015 fatcat:llshlmoijngp7axx5asxzhfn3m

Classification and segmentation of fMRI Spatio-Temporal Brain Data with a NeuCube evolving Spiking Neural Network model

Maryam Gholami Doborjeh, Elisa Capecci, Nikola Kasabov
2014 2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS)  
This paper addresses the problem by means of a novel Spiking Neural Networks (SNN) architecture, called NeuCube [2].  ...  The significant improvement in accuracy is demonstrated as compared with some already published results [3] on the same data sets and traditional machine learning methods.  ...  A block diagram of the NeuCube architecture with its main modules for a case study on fMRI -In the output classification module, supervised learning of the spike sequences is performed using deSNN algorithm  ... 
doi:10.1109/eals.2014.7009506 dblp:conf/eals/DoborjehCK14 fatcat:lzizsc7wpzflfcgy6fie64moia

Cognitive computing systems: Algorithms and applications for networks of neurosynaptic cores

Steve K. Esser, Alexander Andreopoulos, Rathinakumar Appuswamy, Pallab Datta, Davis Barch, Arnon Amir, John Arthur, Andrew Cassidy, Myron Flickner, Paul Merolla, Shyamal Chandra, Nicola Basilico (+11 others)
2013 The 2013 International Joint Conference on Neural Networks (IJCNN)  
The non-von Neumann nature of the TrueNorth architecture necessitates a novel approach to efficient system design.  ...  Marching along the DARPA SyNAPSE roadmap, IBM unveils a trilogy of innovations towards the TrueNorth cognitive computing system inspired by the brain's function and efficiency.  ...  First, one must learn to program a parallel, distributed, event-driven architecture that uses spikes, has discrete-valued synapses, allows each neuron to receive inputs from at most 256 axons, requires  ... 
doi:10.1109/ijcnn.2013.6706746 dblp:conf/ijcnn/EsserAADBAACFMCBCZZAKWRMNSM13 fatcat:bjkz56ezerg4rcxykd7uyyftsi

New Algorithms for Encoding, Learning and Classification of fMRI Data in a Spiking Neural Network Architecture: A Case on Modeling and Understanding of Dynamic Cognitive Processes

Nikola Kasabov, Lei Zhou, Maryam Gholami Doborjeh, Zohreh Gholami Doborjeh, Jie Yang
2017 IEEE Transactions on Cognitive and Developmental Systems  
The paper proposes a novel method based on the NeuCube SNN architecture for which the following new algorithms are introduced: fMRI data encoding into spike sequences; deep unsupervised learning of fMRI  ...  Index Terms-Spiking neural networks, perceptual dynamics, fMRI data, NeuCube, deep learning in spiking neural networks, brain functional connectivity, classification, neuromorphic cognitive systems.  ...  A research question to address in the future is: Based on the results here, which demonstrate that a SNN architecture can be used to model cognitive brain data, can we create neuromorphic cognitive and  ... 
doi:10.1109/tcds.2016.2636291 fatcat:d65yarmtwvcltkktgawoxm7kvy

Symbol manipulation and rule learning in spiking neuronal networks

Chrisantha Fernando
2011 Journal of Theoretical Biology  
using spike-time dependent plasticity based supervised learning.  ...  a kind of natural selection of re-write rules in the brain, We show how the core operation of a learning classifier system, namely, the replication with variation of symbol re-write rules, can be implemented  ...  Thanks to 23 the FP7 E-FLUX EU grant and for a Marie Curie Fellowship to work at Collegium Budapest in Hungary.  ... 
doi:10.1016/j.jtbi.2011.01.009 pmid:21237176 fatcat:iro52il65jgcrf23q6dyzhwkfq

Evolving spiking neural networks for spatio-and spectro-temporal pattern recognition

Nikola Kasabov
This paper provides a survey on the evolution of the evolving connectionist systems (ECOS) paradigm, from simple ECOS introduced in 1998 to evolving spiking neural networks (eSNN) and neurogenetic systems  ...  Abstract This paper provides a survey on the evolution of the evolving connectionist systems (ECOS) paradigm, from simple ECOS introduced in 1998 to evolving spiking neural networks (eSNN) and neurogenetic  ...  Evolving Connectionist Systems (ECOS) Evolving connectionist systems (ECOS) are modular connectionist based systems that evolve their structure and functionality in a continuous, self-organised, on-line  ... 
doi:10.1109/is.2012.6335110 dblp:conf/is/Kasabov12 fatcat:5qa7yzkkjbdc7gy3grz32a4beu

A current-mode spiking neural classifier with lumped dendritic nonlinearity

Amitava Banerjee, Sougata Kar, Subhrajit Roy, Aritra Bhaduri, Arindam Basu
2015 2015 IEEE International Symposium on Circuits and Systems (ISCAS)  
We present the current mode implementation of a spiking neural classifier with lumped square law dendritic nonlinearity.  ...  It has been shown earlier that such a system with binary synapses can be trained with structural plasticity algorithms to achieve comparable classification accuracy with less synaptic resources than conventional  ...  CONCLUSION AND DISCUSSION In this paper, we present the VLSI circuit design in 0.35μm CMOS of a neuromorphic spike based classifier with 8 nonlinear dendrites per neuron and 2 opponent neurons per class  ... 
doi:10.1109/iscas.2015.7168733 dblp:conf/iscas/BanerjeeKRBB15 fatcat:ltvngxttifbcji5ktt5kjbyd6m

A spiking half-cognitive model for classification

Christian R. Huyck, Ritwik Kulkarni
2018 Connection science  
Acknowledgements: This work was supported by the Human Brain Project Grant 604102, Neuromorphic Embodied Agents that Learn. Multi-Layer perceptron code was developed by David Adler.  ...  This paper proposes a cognitive model of classification based on simulated spiking neurons that learn via a Hebbian learning mechanism.  ...  This paper explores to what extent a classifying model, based on spiking Fatiguing Leaky Integrate and Fire (FLIF) neurons [Huyck and Parvizi, 2012] with a modular recurrent architecture, is successful  ... 
doi:10.1080/09540091.2018.1443317 fatcat:cp5hsluosvdxxblr2yc67wmyxe
« Previous Showing results 1 — 15 out of 5,907 results