Sparse Coding by Spiking Neural Networks: Convergence Theory and Computational Results
This provides a foundational guarantee for using SNNs in practical applications like feature extraction, addressing reliability concerns in non von Neumann computing.
The paper tackles the problem of guaranteeing that a spiking neural network (SNN) can reliably solve important computational tasks, specifically sparse coding for feature extraction, and proves that under a moderate assumption, the SNN indeed solves sparse coding, marking the first rigorous result of this kind.
In a spiking neural network (SNN), individual neurons operate autonomously and only communicate with other neurons sparingly and asynchronously via spike signals. These characteristics render a massively parallel hardware implementation of SNN a potentially powerful computer, albeit a non von Neumann one. But can one guarantee that a SNN computer solves some important problems reliably? In this paper, we formulate a mathematical model of one SNN that can be configured for a sparse coding problem for feature extraction. With a moderate but well-defined assumption, we prove that the SNN indeed solves sparse coding. To the best of our knowledge, this is the first rigorous result of this kind.