TY - GEN
T1 - A Suppression-based STDP Rule Resilient to Jitter Noise in Spike Patterns for Neuromorphic Computing
AU - Gautam, Ashish
AU - Kohno, Takashi
AU - Date, Prasanna
AU - Patton, Robert
AU - Potok, Thomas
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Multi-spike models of synaptic plasticity, such as the triplet and suppression spike-timing-dependent plasticity (STDP) rules, exhibit better alignment with neurophysiological data in the brain compared to the pair-based STDP rule. Previous studies have empirically shown that the pair-based STDP rule can detect spatiotemporal spike patterns hidden in equally dense distractor spike trains in an unsupervised manner. However, it fails to detect spike patterns influenced by jitter noise. Given that spiking neural networks (SNNs) exhibit variability in generated spike trains in response to the same inputs, it becomes imperative to have learning rules capable of detecting spike patterns even in the presence of jitter noise. In this study, we introduce a simplified suppression-based STDP rule that demonstrates significantly enhanced tolerance to jitter in spike patterns compared to the pair-based STDP rule. Unlike the ideal suppression STDP rule, characterized by an exponential learning window and requiring high-resolution synapses, the simplified rule limits the synaptic efficacy update to a single bit at any given instant. Moreover, it employs 4-bit fixed-point synapses, facilitating straightforward implementation in neuromorphic hardware.
AB - Multi-spike models of synaptic plasticity, such as the triplet and suppression spike-timing-dependent plasticity (STDP) rules, exhibit better alignment with neurophysiological data in the brain compared to the pair-based STDP rule. Previous studies have empirically shown that the pair-based STDP rule can detect spatiotemporal spike patterns hidden in equally dense distractor spike trains in an unsupervised manner. However, it fails to detect spike patterns influenced by jitter noise. Given that spiking neural networks (SNNs) exhibit variability in generated spike trains in response to the same inputs, it becomes imperative to have learning rules capable of detecting spike patterns even in the presence of jitter noise. In this study, we introduce a simplified suppression-based STDP rule that demonstrates significantly enhanced tolerance to jitter in spike patterns compared to the pair-based STDP rule. Unlike the ideal suppression STDP rule, characterized by an exponential learning window and requiring high-resolution synapses, the simplified rule limits the synaptic efficacy update to a single bit at any given instant. Moreover, it employs 4-bit fixed-point synapses, facilitating straightforward implementation in neuromorphic hardware.
KW - jitter noise
KW - lateral inhibition
KW - low-resolution synapse
KW - Multi-spike STDP model
KW - neuromorphic computing
KW - spike pattern detection
KW - suppression STDP rule
KW - Triplet STDP rule
UR - http://www.scopus.com/inward/record.url?scp=85214701881&partnerID=8YFLogxK
U2 - 10.1109/ICONS62911.2024.00037
DO - 10.1109/ICONS62911.2024.00037
M3 - Conference contribution
AN - SCOPUS:85214701881
T3 - Proceedings - 2024 International Conference on Neuromorphic Systems, ICONS 2024
SP - 209
EP - 216
BT - Proceedings - 2024 International Conference on Neuromorphic Systems, ICONS 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 International Conference on Neuromorphic Systems, ICONS 2024
Y2 - 30 July 2024 through 2 August 2024
ER -