Walters, Ben, Bethi, Yeshwanth, Kalatehbali, Hamid Rahimian, Afshar, Saeed, Amirsoleimani, Amirali, and Rahimi Azghadi, Mostafa (2025) Spiking Auto-Encoder for Static and Spatio-Temporal Neuromorphic Pattern Reconstruction. In: Proceedings of the IEEE International Symposium on Circuits and Systems. From: ISCAS 2025: IEEE International Symposium on Circuits and Systems, 25-28 May 2025, London, UK.

PDF (Published Version) - Published Version Restricted to Repository staff only

Abstract

Spiking Auto-Encoders (SAEs) have the potential to greatly outperform deep learning auto-encoders in power efficiency, yet their performance remains a challenge. This work enhances both power efficiency and accuracy by reducing spike counts and introducing key innovations. We propose a novel decoder neuron model that enables precise spike timing and implement a weight-dependent Spike-Timing-Dependent Plasticity (STDP) mechanism in the encoder for better feature learning. Our architecture encodes static MNIST images using only a single spike and reconstructs spatio-temporal data from the Spiking Heidelberg Digits (SHD) dataset, optimizing the spike count for reconstruction. This substantial reduction in spike usage translates to a marked improvement in power efficiency. In addition, the average Mean Square Error (MSE) for the MNIST images was found to be 0.039, representing a 99.93% reduction from previous results. These improvements advance neuromorphic systems toward more practical, efficient applications.

Actions (Repository Staff Only)

Item Control Page