🤖 AI Summary
This work addresses the fundamental challenge in spiking neural networks (SNNs) of reconciling convolutional weight sharing with the biological constraint of local synaptic plasticity. To this end, we propose a biologically inspired convolutional SNN architecture for image classification. Our method comprises two key components: (1) employing fixed, pre-defined convolutional kernels for feedforward feature extraction—thereby preserving locality in spike-timing-dependent plasticity (STDP) or other local learning rules—and (2) introducing a data-driven initialization strategy based on domain-specific image sets to enhance both the biological plausibility and discriminative power of the initial kernels. Evaluated on the NEOVISION2 benchmark, our approach significantly improves feature representation capability and inference efficiency while maintaining high classification accuracy and strong biological interpretability. To the best of our knowledge, this is the first demonstration that a fixed convolutional structure can be effectively co-optimized with spiking dynamics to achieve competitive performance, thereby validating a novel paradigm for biologically grounded deep SNN design.
📝 Abstract
We consider an implementation of convolutional architecture in a spiking neural network (SNN) used to classify images. As in the traditional neural network, the convolutional layers form informational"features"used as predictors in the SNN-based classifier with CoLaNET architecture. Since weight sharing contradicts the synaptic plasticity locality principle, the convolutional weights are fixed in our approach. We describe a methodology for their determination from a representative set of images from the same domain as the classified ones. We illustrate and test our approach on a classification task from the NEOVISION2 benchmark.