Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Apr;117(1-2):95-111.
doi: 10.1007/s00422-023-00956-x. Epub 2023 Apr 1.

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

Melani Sanchez-Garcia  1 , Tushar Chauhan  2   3 , Benoit R Cottereau  3   4 , Michael Beyeler  5   6
Affiliations

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

Melani Sanchez-Garcia et al. Biol Cybern. 2023 Apr.

Abstract

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. 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.

Keywords: Multi-scale processing; Spike-latency code; Spike-timing-dependent-plasticity; Spiking neural networks; Winner-take-all inhibition.

PubMed Disclaimer

Similar articles

See all similar articles

Cited by

References

    1. Ales JM, Appelbaum LG, Cottereau BR et al (2013) The time course of shape discrimination in the human brain. Neuroimage 67:77–88 - PubMed - DOI
    1. Beyeler M, Dutt ND, Krichmar JL (2013) Categorization and decision-making in a neurobiologically plausible spiking network using a STDP-like learning rule. Neural Netw 48:109–24 - PubMed - DOI
    1. Beyeler M, Dutt N, Krichmar JL (2016) 3D visual response properties of MSTd emerge from an efficient, sparse population code. J Neurosci 36(32):8399–8415 - PubMed - PMC - DOI
    1. Beyeler M, Rounds E, Carlson K et al (2019) Neural correlates of sparse coding and dimensionality reduction. PLoS Comput Biol 15(6):e1006908 - PubMed - PMC - DOI
    1. Bi GQ, Poo MM (1998) Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. J Neurosci 18(24):10,464-10,472

Publication types

LinkOut - more resources

-