mlsanityData to 7 Oct 2026

Characterization of Generalizability of Spike Timing Dependent Plasticity trained Spiking Neural Networks

arXiv 2105.14677 ↗First posted 31 May 2021cs.NE cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

A Spiking Neural Network (SNN) is trained with Spike Timing Dependent Plasticity (STDP), which is a neuro-inspired unsupervised learning method for various machine learning applications. This paper studies the generalizability properties of the STDP learning processes using the Hausdorff dimension of the trajectories of the learning algorithm. The paper analyzes the effects of STDP learning models and associated hyper-parameters on the generalizability properties of an SNN. The analysis is used to develop a Bayesian optimization approach to optimize the hyper-parameters for an STDP model for improving the generalizability properties of an SNN.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 15 of its 73 references that are in the map. First posted on arXiv 31 May 2021.

Builds on

15 of 73 references.

References · 15

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2017Exploring Generalization in Deep Learningcited by 595
  3. 2018Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layerscited by 340
  4. 2019A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networkscited by 213
  5. 2017Generalization in Deep Learningcited by 146
  6. 2020The Heavy-Tail Phenomenon in SGDcited by 122
  7. 2020Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networkscited by 62
  8. 2018Comparing Dynamics: Deep Neural Networks versus Glassy Systemscited by 42
  9. 2020Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noisecited by 33
  10. 2018Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networkscited by 25
  11. 2016STDP-based spiking deep convolutional neural networks for object recognitioncited by 24
  12. 2019Can SGD Learn Recurrent Neural Networks with Provable Generalization?cited by 17
3 more
  1. 2017ASP: Learning to Forget with Adaptive Synaptic Plasticity in Spiking Neural Networkscited by 15
  2. 2020Anomalous diffusion dynamics of learning in deep neural networkscited by 9
  3. 2020Stochastic Models of Neural Synaptic Plasticitycited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 4; 2025: 1.

8 papers.

  1. 2024Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNNcited by 10
  2. 2023Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principlescited by 8
  3. 2023Brain-Inspired Spiking Neural Network for Online Unsupervised Time Series Predictioncited 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. 2022Functional Connectome: Approximating Brain Networks with Artificial Neural Networkscited by 1
  7. 2024A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networkscited by 1
  8. 2025FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learningcited by 1