# A New Look at Spike-Timing-Dependent Plasticity Networks for Spatio-Temporal Feature Learning

arXiv: https://arxiv.org/abs/2111.00791 · HTML: https://mlsanity.com/paper/2111.00791/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 48 references that are in the map.
- First posted on arXiv 1 Nov 2021.

## Builds on (most cited first, 17 of 17)

- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification](https://mlsanity.com/paper/1803.07913/) (2018)
- [Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks](https://mlsanity.com/paper/2103.12593/) (2021)
- [Dendritic cortical microcircuits approximate the backpropagation algorithm](https://mlsanity.com/paper/1810.11393/) (2018)
- [DART: Distribution Aware Retinal Transform for Event-based Cameras](https://mlsanity.com/paper/1710.10800/) (2017)
- [An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processor](https://mlsanity.com/paper/2006.09985/) (2020)
- [Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction](https://mlsanity.com/paper/2003.12346/) (2020)
- [Low-Power Neuromorphic Hardware for Signal Processing Applications](https://mlsanity.com/paper/1901.03690/) (2019)
- [Convolutional Dictionary Learning via Local Processing](https://mlsanity.com/paper/1705.03239/) (2017)
- [Is Neuromorphic MNIST neuromorphic? Analyzing the discriminative power of neuromorphic datasets in the time domain](https://mlsanity.com/paper/1807.01013/) (2018)
- [Multi-layered Spiking Neural Network with Target Timestamp Threshold Adaptation and STDP](https://mlsanity.com/paper/1904.01908/) (2019)
- [Unsupervised AER Object Recognition Based on Multiscale Spatio-Temporal Features and Spiking Neurons](https://mlsanity.com/paper/1911.08261/) (2019)
- [Unsupervised Visual Feature Learning with Spike-timing-dependent Plasticity: How Far are we from Traditional Feature Learning Approaches?](https://mlsanity.com/paper/1901.04392/) (2019)
- [Ultra Low-Power and Real-time ECG Classification Based on STDP and R-STDP Neural Networks for Wearable Devices](https://mlsanity.com/paper/1905.02954/) (2019)
- [Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation](https://mlsanity.com/paper/2009.11044/) (2020)

## Built on by (most cited first, 3 of 3)

- [Fusing Event-based Camera and Radar for SLAM Using Spiking Neural Networks with Continual STDP Learning](https://mlsanity.com/paper/2210.04236/) (2022)
- [Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications](https://mlsanity.com/paper/2410.09218/) (2024)
- [Active Inference in Hebbian Learning Networks](https://mlsanity.com/paper/2306.05053/) (2023)

## Abstract (arXiv)

We present new theoretical foundations for unsupervised Spike-Timing-Dependent Plasticity (STDP) learning in spiking neural networks (SNNs). In contrast to empirical parameter search used in most previous works, we provide novel theoretical grounds for SNN and STDP parameter tuning which considerably reduces design time. Using our generic framework, we propose a class of global, action-based and convolutional SNN-STDP architectures for learning spatio-temporal features from event-based cameras. We assess our methods on the N-MNIST, the CIFAR10-DVS and the IBM DVS128 Gesture datasets, all acquired with a real-world event camera. Using our framework, we report significant improvements in classification accuracy compared to both conventional state-of-the-art event-based feature descriptors (+8.2% on CIFAR10-DVS), and compared to state-of-the-art STDP-based systems (+9.3% on N-MNIST, +7.74% on IBM DVS128 Gesture). Our work contributes to both ultra-low-power learning in neuromorphic edge devices, and towards a biologically-plausible, optimization-based theory of cortical vision.