Spiking Generative Adversarial Networks With a Neural Network Discriminator: Local Training, Bayesian Models, and Continual Meta-Learning

no code implementations • 2 Nov 2021 • Bleema Rosenfeld, Osvaldo Simeone, Bipin Rajendran

Accordingly, a central problem in neuromorphic computing is training spiking neural networks (SNNs) to reproduce spatio-temporal spiking patterns in response to given spiking stimuli.

Generative Adversarial Network Meta-Learning

Fast On-Device Adaptation for Spiking Neural Networks via Online-Within-Online Meta-Learning

no code implementations • 21 Feb 2021 • Bleema Rosenfeld, Bipin Rajendran, Osvaldo Simeone

Spiking Neural Networks (SNNs) have recently gained popularity as machine learning models for on-device edge intelligence for applications such as mobile healthcare management and natural language processing due to their low power profile.

Management Meta-Learning

Learning First-to-Spike Policies for Neuromorphic Control Using Policy Gradients

no code implementations • 23 Oct 2018 • Bleema Rosenfeld, Osvaldo Simeone, Bipin Rajendran

In this work, the use of SNNs as stochastic policies is explored under an energy-efficient first-to-spike action rule, whereby the action taken by the RL agent is determined by the occurrence of the first spike among the output neurons.

Reinforcement Learning (RL)