The Algorithmic Power of Spiking Neural Networks
Speaker: Chi-NingTitle: The Algorithmic Power of Spiking Neural Networks
Date: 11 Feb 2019 5:30pm-7:00pm
Location: Maxwell-Dworkin 221
Food: TBD
Abstract: Spiking neural networks (SNNs) are mathematical models for biological neural networks such as our brain. In this work, we study SNNs through the lens of algorithms. In particular, we show that the firing rate of the integrate-and-fire SNN can efficiently solve the non-negative least squares problem and $\ell_1$ minimization problem. Further, our proof gives new interpretations on the integrate-and-fire SNN where the external charging and spiking effects can be viewed as gradient and projection respectively in the dual space.
In the first part of this talk, I will give an overview on spiking neural networks and our methodologies. In the rest of the time, I will focus on the details of our technical proof, which is basically an analysis on a variant of projected gradient descent algorithm.
Reference: