mlsanityData to 7 Oct 2026

Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles

arXiv 2302.11618 ↗First posted 22 Feb 2023cs.AI cs.NEcited by 8

Not on the map. Why?

Abstract (arXiv)

This paper shows that the heterogeneity in neuronal and synaptic dynamics reduces the spiking activity of a Recurrent Spiking Neural Network (RSNN) while improving prediction performance, enabling spike-efficient (unsupervised) learning. We analytically show that the diversity in neurons' integration/relaxation dynamics improves an RSNN's ability to learn more distinct input patterns (higher memory capacity), leading to improved classification and prediction performance. We further prove that heterogeneous Spike-Timing-Dependent-Plasticity (STDP) dynamics of synapses reduce spiking activity but preserve memory capacity. The analytical results motivate Heterogeneous RSNN design using Bayesian optimization to determine heterogeneity in neurons and synapses to improve E, defined as the ratio of spiking activity and memory capacity. The empirical results on time series classification and prediction tasks show that optimized HRSNN increases performance and reduces spiking activity compared to a homogeneous RSNN.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 24 of its 86 references that are in the map. First posted on arXiv 22 Feb 2023.

Builds on

24 of 86 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018A Tutorial on Bayesian Optimizationcited by 734
  3. 2017Deep Neural Networks as Gaussian Processescited by 617
  4. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  5. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  6. 2019A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networkscited by 213
  7. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 174
  8. 2019The Heidelberg spiking datasets for the systematic evaluation of spiking neural networkscited by 135
  9. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 98
  10. 2020Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networkscited by 62
  11. 2020Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networkscited by 43
  12. 2019Optimizing the energy consumption of spiking neural networks for neuromorphic applicationscited by 34
12 more
  1. 2021A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detectioncited by 31
  2. 2017Predicting non-linear dynamics by stable local learning in a recurrent spiking neural networkcited by 12
  3. 2019ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computingcited by 12
  4. 2022Heterogeneous Recurrent Spiking Neural Network for Spatio-Temporal Classificationcited by 11
  5. 2020Deep Time-Delay Reservoir Computing: Dynamics and Memory Capacitycited by 10
  6. 2021Characterization of Generalizability of Spike Timing Dependent Plasticity trained Spiking Neural Networkscited by 8
  7. 2021Interacting Hawkes processes with multiplicative inhibitioncited by 6
  8. 2015Modeling networks of spiking neurons as interacting processes with memory of variable lengthcited by 4
  9. 2016Spatiotemporal dynamics and reliable computations in recurrent spiking neural networkscited by 2
  10. 2022Learning in Feedback-driven Recurrent Spiking Neural Networks using full-FORCE Trainingcited by 2
  11. 2015Firing Rate Dynamics in Recurrent Spiking Neural Networks with Intrinsic and Network Heterogeneitycited by 1
  12. 2015Microscopic approach of a time elapsed neural modelcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 5; 2025: 2.

8 papers.

  1. 2024Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNNcited by 10
  2. 2023Brain-Inspired Spiking Neural Network for Online Unsupervised Time Series Predictioncited by 5
  3. 2024Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoningcited by 5
  4. 2024Topological Representations of Heterogeneous Learning Dynamics of Recurrent Spiking Neural Networkscited by 3
  5. 2024Exploiting Heterogeneity in Timescales for Sparse Recurrent Spiking Neural Networks for Energy-Efficient Edge Computingcited by 2
  6. 2024A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networkscited by 1
  7. 2025FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learningcited by 1
  8. 2025HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapsescited by 0