Hyperparameter Optimization in Binary Communication Networks for Neuromorphic Deployment

Abstract

Training neural networks for neuromorphic deployment is non-trivial. There have been a variety of approaches proposed to adapt back-propagation or back-propagation-like algorithms appropriate for training. Considering that these networks often have very different performance characteristics than traditional neural networks, it is often unclear how to set either the network topology or the hyperparameters to achieve optimal performance. In this work, we introduce a Bayesian approach for optimizing the hyperparameters of an algorithm for training binary communication networks that can be deployed to neuromorphic hardware. We show that by optimizing the hyperparameters on this algorithm for each dataset, we can achieve improvements in accuracy over the previous state-of-theart for this algorithm on each dataset (by up to 15 percent). This jump in performance continues to emphasize the potential when converting traditional neural networks to binary communication applicable to neuromorphic hardware.

Bayesian Multi-objective Hyperparameter Optimization for Accurate, Fast, and Efficient Neural Network Accelerator Design

“…Various techniques proposed for training spiking neural networks with different underlying hardware, are vital steps toward efficient neuromorphic computing for edge devices; however, each of these approaches require several hyperparameters and their optimum performance depend on prior knowledge on how to set these hyperparameters. In Parsa et al (2020), we showed that an optimum set of hyperparameters drastically increases the neuromorphic system performance.…”