Sparse Coding by Spiking Neural Networks: Convergence Theory and Computational Results

Abstract

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.

13 pages, 3 figures

Cited by in corpus (9)

• RANC: Reconfigurable Architecture for Neuromorphic Computing
• Fast and Accurate Sparse Coding of Visual Stimuli with a Simple, Ultra-Low-Energy Spiking Architecture
• Exploitation of Image Statistics with Sparse Coding in the Case of Stereo Vision
• Dictionary Learning by Dynamical Neural Networks
• Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons
• Local Information with Feedback Perturbation Suffices for Dictionary Learning in Neural Circuits
• Pre-Synaptic Pool Modification (PSPM): A Supervised Learning Procedure for Spiking Neural Networks
• Improving Spiking Sparse Recovery via Non-Convex Penalties
• Deep Medical Image Analysis with Representation Learning and Neuromorphic Computing