Efficient multi-scale representation of visual objects using a biologically plausible spike-latency code and winner-take-all inhibition

Sanchez-Garcia, Melani; Chauhan, Tushar; Cottereau, Benoit R.; Beyeler, Michael

doi:10.1007/s00422-023-00956-x

Title: Efficient multi-scale representation of visual objects using a biologically plausible spike-latency code and winner-take-all inhibition

Journal Article · Sat Apr 01 00:00:00 EDT 2023 · Biological Cybernetics (Online)

DOI:https://doi.org/10.1007/s00422-023-00956-x· OSTI ID:1991821

Sanchez-Garcia, Melani ^[1]; Chauhan, Tushar ^[2]; Cottereau, Benoit R. ^[3]; Beyeler, Michael ^[1]

University of California, Santa Barbara, CA (United States)
Massachusetts Institute of Technology (MIT), Boston, MA (United States); Université de Toulouse III-Paul Sabatier (France)
Université de Toulouse III-Paul Sabatier (France); IPAL, CNRS IRL (Singapore)

Deep neural networks have surpassed human performance in key visual challenges such as object recognition, but require a large amount of energy, computation, and memory. In contrast, spiking neural networks (SNNs) have the potential to improve both the efficiency and biological plausibility of object recognition systems. Here we present a SNN model that uses spike-latency coding and winner-take-all inhibition (WTA-I) to efficiently represent visual stimuli using multi-scale parallel processing. Mimicking neuronal response properties in early visual cortex, images were preprocessed with three different spatial frequency (SF) channels, before they were fed to a layer of spiking neurons whose synaptic weights were updated using spike-timing-dependent-plasticity. We investigate how the quality of the represented objects changes under different SF bands and WTA-I schemes. We demonstrate that a network of 200 spiking neurons tuned to three SFs can efficiently represent objects with as little as 15 spikes per neuron. Furthermore, studying how core object recognition may be implemented using biologically plausible learning rules in SNNs may not only further our understanding of the brain, but also lead to novel and efficient artificial vision systems.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

Grant/Contract Number:: SC0022997

OSTI ID:: 1991821

Journal Information:: Biological Cybernetics (Online), Vol. 117, Issue 1-2; ISSN 1432-0770

Publisher:: SpringerCopyright Statement

Country of Publication:: United States

Language:: English

References (46)

Learning Input Correlations through Nonlinear Temporally Asymmetric Hebbian Plasticity Gütig, R.; Aharonov, R.; Rotter, S. The Journal of Neuroscience, Vol. 23, Issue 9 https://doi.org/10.1523/JNEUROSCI.23-09-03697.2003	journal	May 2003
Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity Masquelier, Timothée; Thorpe, Simon J. PLoS Computational Biology, Vol. 3, Issue 2 https://doi.org/10.1371/journal.pcbi.0030031	journal	February 2007
Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks Mozafari, Milad; Ganjtabesh, Mohammad; Nowzari-Dalini, Abbas Pattern Recognition, Vol. 94 https://doi.org/10.1016/j.patcog.2019.05.015	journal	October 2019
Amplitude spectra of natural images Tolhurst, D. J.; Tadmor, Y.; Chao, Tang Ophthalmic and Physiological Optics, Vol. 12, Issue 2 https://doi.org/10.1111/j.1475-1313.1992.tb00296.x	journal	April 1992
The neural bases of spatial frequency processing during scene perception Kauffmann, Louise; RamanoÃ«l, Stephen; Peyrin, Carole Frontiers in Integrative Neuroscience, Vol. 8 https://doi.org/10.3389/fnint.2014.00037	journal	May 2014
Similarity-Based Fusion of MEG and fMRI Reveals Spatio-Temporal Dynamics in Human Cortex During Visual Object Recognition Cichy, Radoslaw Martin; Pantazis, Dimitrios; Oliva, Aude Cerebral Cortex, Vol. 26, Issue 8 https://doi.org/10.1093/cercor/bhw135	journal	May 2016
Spatial Frequency Analysis in the Visual System Shapley, Robert; Lennie, Peter Annual Review of Neuroscience, Vol. 8, Issue 1 https://doi.org/10.1146/annurev.ne.08.030185.002555	journal	March 1985
A Bio-Inspired Hierarchical Spiking Neural Network With Reward-Modulated STDP Learning Rule for AER Object Recognition Zhou, Qian; Li, Xiaohu IEEE Sensors Journal, Vol. 22, Issue 16 https://doi.org/10.1109/JSEN.2022.3189679	journal	August 2022
The influence of temporal frequency and adaptation level on receptive field organization of retinal ganglion cells in cat Derrington, A. M.; Lennie, P. The Journal of Physiology, Vol. 333, Issue 1 https://doi.org/10.1113/jphysiol.1982.sp014457	journal	December 1982
Relations between the statistics of natural images and the response properties of cortical cells Field, David J. Journal of the Optical Society of America A, Vol. 4, Issue 12 https://doi.org/10.1364/JOSAA.4.002379	journal	January 1987
μBrain: An Event-Driven and Fully Synthesizable Architecture for Spiking Neural Networks Stuijt, Jan; Sifalakis, Manolis; Yousefzadeh, Amirreza Frontiers in Neuroscience, Vol. 15 https://doi.org/10.3389/fnins.2021.664208	journal	May 2021
On the Computational Power of Winner-Take-All Maass, Wolfgang Neural Computation, Vol. 12, Issue 11 https://doi.org/10.1162/089976600300014827	journal	November 2000
Emergence of Binocular Disparity Selectivity through Hebbian Learning Chauhan, Tushar; Masquelier, Timothée; Montlibert, Alexandre The Journal of Neuroscience, Vol. 38, Issue 44 https://doi.org/10.1523/JNEUROSCI.1259-18.2018	journal	September 2018
Deep Learning for Multilabel Land Cover Scene Categorization Using Data Augmentation Stivaktakis, Radamanthys; Tsagkatakis, Grigorios; Tsakalides, Panagiotis IEEE Geoscience and Remote Sensing Letters, Vol. 16, Issue 7 https://doi.org/10.1109/LGRS.2019.2893306	journal	July 2019
Simple Learned Weighted Sums of Inferior Temporal Neuronal Firing Rates Accurately Predict Human Core Object Recognition Performance Majaj, N. J.; Hong, H.; Solomon, E. A. Journal of Neuroscience, Vol. 35, Issue 39 https://doi.org/10.1523/JNEUROSCI.5181-14.2015	journal	September 2015
A biologically plausible supervised learning method for spiking neural networks using the symmetric STDP rule Hao, Yunzhe; Huang, Xuhui; Dong, Meng Neural Networks, Vol. 121 https://doi.org/10.1016/j.neunet.2019.09.007	journal	January 2020
Categorization and decision-making in a neurobiologically plausible spiking network using a STDP-like learning rule Beyeler, Michael; Dutt, Nikil D.; Krichmar, Jeffrey L. Neural Networks, Vol. 48 https://doi.org/10.1016/j.neunet.2013.07.012	journal	December 2013
STDP-based spiking deep convolutional neural networks for object recognition Kheradpisheh, Saeed Reza; Ganjtabesh, Mohammad; Thorpe, Simon J. Neural Networks, Vol. 99 https://doi.org/10.1016/j.neunet.2017.12.005	journal	March 2018
Neuromodulation of Spike-Timing-Dependent Plasticity: Past, Present, and Future Brzosko, Zuzanna; Mierau, Susanna B.; Paulsen, Ole Neuron, Vol. 103, Issue 4 https://doi.org/10.1016/j.neuron.2019.05.041	journal	August 2019
Face identification using one spike per neuron: resistance to image degradations Delorme, A.; Thorpe, S. J. Neural Networks, Vol. 14, Issue 6-7 https://doi.org/10.1016/S0893-6080(01)00049-1	journal	July 2001
Sparse Coding and Decorrelation in Primary Visual Cortex During Natural Vision Vinje, W. E. Science, Vol. 287, Issue 5456 https://doi.org/10.1126/science.287.5456.1273	journal	February 2000
Rapid Feedforward Computation by Temporal Encoding and Learning With Spiking Neurons IEEE Transactions on Neural Networks and Learning Systems, Vol. 24, Issue 10 https://doi.org/10.1109/TNNLS.2013.2245677	journal	October 2013
The time course of shape discrimination in the human brain Ales, Justin M.; Appelbaum, L. Gregory; Cottereau, Benoit R. NeuroImage, Vol. 67 https://doi.org/10.1016/j.neuroimage.2012.10.044	journal	February 2013
Multi-layered Spiking Neural Network with Target Timestamp Threshold Adaptation and STDP Falez, Pierre; Tirilly, Pierre; Marius Bilasco, Ioan 2019 International Joint Conference on Neural Networks (IJCNN) https://doi.org/10.1109/IJCNN.2019.8852346	conference	July 2019
Extraclassical Receptive Field Properties of Parvocellular, Magnocellular, and Koniocellular Cells in the Primate Lateral Geniculate Nucleus Solomon, Samuel G.; White, Andrew J. R.; Martin, Paul R. The Journal of Neuroscience, Vol. 22, Issue 1 https://doi.org/10.1523/JNEUROSCI.22-01-00338.2002	journal	January 2002
Supervised Learning in SNN via Reward-Modulated Spike-Timing-Dependent Plasticity for a Target Reaching Vehicle Bing, Zhenshan; Baumann, Ivan; Jiang, Zhuangyi Frontiers in Neurorobotics, Vol. 13 https://doi.org/10.3389/fnbot.2019.00018	journal	May 2019
Unsupervised learning of digit recognition using spike-timing-dependent plasticity Diehl, Peter U.; Cook, Matthew Frontiers in Computational Neuroscience, Vol. 9 https://doi.org/10.3389/fncom.2015.00099	journal	August 2015
The Spike-Timing Dependence of Plasticity Feldman, Daniel E. Neuron, Vol. 75, Issue 4 https://doi.org/10.1016/j.neuron.2012.08.001	journal	August 2012
The mechanism of peripherally evoked responses in retinal ganglion cells. Derrington, A. M.; Lennie, P.; Wright, M. J. The Journal of Physiology, Vol. 289, Issue 1 https://doi.org/10.1113/jphysiol.1979.sp012738	journal	April 1979
Global Precedence, Spatial Frequency Channels, and the Statistics of Natural Images Hughes, Howard C.; Nozawa, George; Kitterle, Frederick Journal of Cognitive Neuroscience, Vol. 8, Issue 3 https://doi.org/10.1162/jocn.1996.8.3.197	journal	July 1996
How Does the Brain Solve Visual Object Recognition? DiCarlo, James J.; Zoccolan, Davide; Rust, Nicole C. Neuron, Vol. 73, Issue 3 https://doi.org/10.1016/j.neuron.2012.01.010	journal	February 2012
Unsupervised AER Object Recognition Based on Multiscale Spatio-Temporal Features and Spiking Neurons Liu, Qianhui; Pan, Gang; Ruan, Haibo IEEE Transactions on Neural Networks and Learning Systems, Vol. 31, Issue 12 https://doi.org/10.1109/TNNLS.2020.2966058	journal	December 2020
A Survey of Methods for Low-Power Deep Learning and Computer Vision Goel, Abhinav; Tung, Caleb; Lu, Yung-Hsiang 2020 IEEE 6th World Forum on Internet of Things (WF-IoT) https://doi.org/10.1109/WF-IoT48130.2020.9221198	conference	June 2020
Parallel processing strategies of the primate visual system Nassi, Jonathan J.; Callaway, Edward M. Nature Reviews Neuroscience, Vol. 10, Issue 5 https://doi.org/10.1038/nrn2619	journal	April 2009
Synaptic Modifications in Cultured Hippocampal Neurons: Dependence on Spike Timing, Synaptic Strength, and Postsynaptic Cell Type Bi, Guo-qiang; Poo, Mu-ming The Journal of Neuroscience, Vol. 18, Issue 24 https://doi.org/10.1523/JNEUROSCI.18-24-10464.1998	journal	December 1998
Spike Timing–Dependent Plasticity: A Hebbian Learning Rule Caporale, Natalia; Dan, Yang Annual Review of Neuroscience, Vol. 31, Issue 1 https://doi.org/10.1146/annurev.neuro.31.060407.125639	journal	July 2008
Spatial frequency tuning in human retinotopic visual areas Henriksson, L.; Nurminen, L.; Hyvarinen, A. Journal of Vision, Vol. 8, Issue 10 https://doi.org/10.1167/8.10.5	journal	August 2008
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing 2015 IEEE International Conference on Computer Vision (ICCV) https://doi.org/10.1109/ICCV.2015.123	conference	December 2015
3D Visual Response Properties of MSTd Emerge from an Efficient, Sparse Population Code Beyeler, M.; Dutt, N.; Krichmar, J. L. Journal of Neuroscience, Vol. 36, Issue 32 https://doi.org/10.1523/JNEUROSCI.0396-16.2016	journal	August 2016
The contrast sensitivity of retinal ganglion cells of the cat Enroth-Cugell, Christina; Robson, J. G. The Journal of Physiology, Vol. 187, Issue 3 https://doi.org/10.1113/jphysiol.1966.sp008107	journal	December 1966
Sub-Optimality of the Early Visual System Explained Through Biologically Plausible Plasticity Chauhan, Tushar; Masquelier, Timothée; Cottereau, Benoit R. Frontiers in Neuroscience, Vol. 15 https://doi.org/10.3389/fnins.2021.727448	journal	September 2021
A Review of Yolo Algorithm Developments Jiang, Peiyuan; Ergu, Daji; Liu, Fangyao Procedia Computer Science, Vol. 199 https://doi.org/10.1016/j.procs.2022.01.135	journal	January 2022
The Code for Facial Identity in the Primate Brain Chang, Le; Tsao, Doris Y. Cell, Vol. 169, Issue 6 https://doi.org/10.1016/j.cell.2017.05.011	journal	June 2017
An ensemble unsupervised spiking neural network for objective recognition Fu, Qiang; Dong, Hongbin Neurocomputing, Vol. 419 https://doi.org/10.1016/j.neucom.2020.07.109	journal	January 2021
Spatial frequency selectivity of cells in macaque visual cortex De Valois, Russell L.; Albrecht, Duane G.; Thorell, Lisa G. Vision Research, Vol. 22, Issue 5, p. 545-559 https://doi.org/10.1016/0042-6989(82)90113-4	journal	January 1982
Neural correlates of sparse coding and dimensionality reduction Beyeler, Michael; Rounds, Emily L.; Carlson, Kristofor D. PLOS Computational Biology, Vol. 15, Issue 6 https://doi.org/10.1371/journal.pcbi.1006908	journal	June 2019

Similar Records

A Hardware and Software Co-design Framework for Energy Efficient Neuromorphic Systems

Technical Report · Wed Jul 05 00:00:00 EDT 2023 · OSTI ID:1991821

Li, Hai; Taylor, Brady

Design of a Robust Memristive Spiking Neuromorphic System with Unsupervised Learning in Hardware

Journal Article · Wed Jun 30 00:00:00 EDT 2021 · ACM Journal on Emerging Technologies in Computing Systems · OSTI ID:1991821

Adnan, Md Musabbir; Sayyaparaju, Sagarvarma; Brown, Samuel D.; +3 more

Modular Spiking Neural Circuits for Mapping Long Short-Term Memory on a Neurosynaptic Processor

Journal Article · Fri Jul 13 00:00:00 EDT 2018 · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · OSTI ID:1991821

Shrestha, Amar; Ahmed, Khadeer; Wang, Yanzhi; +4 more

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
Spiking neural networks
Spike-timing-dependent-plasticity
Multi-scale processing
Spike-latency code
Winner-take-all inhibition

Title: Efficient multi-scale representation of visual objects using a biologically plausible spike-latency code and winner-take-all inhibition

Citation Formats

References (46)

Similar Records

Related Subjects