Efficient multi-scale representation of visual objects using a biologically plausible spike-latency code and winner-take-all inhibition
- PMID: 37004546
- DOI: 10.1007/s00422-023-00956-x
Efficient multi-scale representation of visual objects using a biologically plausible spike-latency code and winner-take-all inhibition
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.
© 2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
Similar articles
-
Competitive Learning in a Spiking Neural Network: Towards an Intelligent Pattern Classifier.Sensors (Basel). 2020 Jan 16;20(2):500. doi: 10.3390/s20020500. Sensors (Basel). 2020. PMID: 31963143 Free PMC article.
-
A review of learning in biologically plausible spiking neural networks.Neural Netw. 2020 Feb;122:253-272. doi: 10.1016/j.neunet.2019.09.036. Epub 2019 Oct 11. Neural Netw. 2020. PMID: 31726331 Review.
-
A biologically plausible supervised learning method for spiking neural networks using the symmetric STDP rule.Neural Netw. 2020 Jan;121:387-395. doi: 10.1016/j.neunet.2019.09.007. Epub 2019 Sep 27. Neural Netw. 2020. PMID: 31593843
-
Deep learning in spiking neural networks.Neural Netw. 2019 Mar;111:47-63. doi: 10.1016/j.neunet.2018.12.002. Epub 2018 Dec 18. Neural Netw. 2019. PMID: 30682710 Review.
-
STDP-based spiking deep convolutional neural networks for object recognition.Neural Netw. 2018 Mar;99:56-67. doi: 10.1016/j.neunet.2017.12.005. Epub 2017 Dec 23. Neural Netw. 2018. PMID: 29328958
Cited by
-
Towards aSmart Bionic Eye: AI-powered artificial vision for the treatment of incurable blindness.J Neural Eng. 2022 Dec 7;19(6):10.1088/1741-2552/aca69d. doi: 10.1088/1741-2552/aca69d. J Neural Eng. 2022. PMID: 36541463 Free PMC article.
References
-
- 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
MeSH terms
LinkOut - more resources
Full Text Sources