Accurate and Energy-Efficient Classification with Spiking Random Neural Network: Corrected and Expanded Version
This addresses the problem of energy consumption in neural network deployment for industries and researchers, though it appears incremental as it adapts an existing spiking model to classification tasks.
The paper tackles the high computational and power costs of Artificial Neural Networks (ANNs) by proposing a Spiking Random Neural Network (RNN) as an energy-efficient alternative, demonstrating that it matches ANN classification accuracy on real-world datasets.
Artificial Neural Network (ANN) based techniques have dominated state-of-the-art results in most problems related to computer vision, audio recognition, and natural language processing in the past few years, resulting in strong industrial adoption from all leading technology companies worldwide. One of the major obstacles that have historically delayed large scale adoption of ANNs is the huge computational and power costs associated with training and testing (deploying) them. In the mean-time, Neuromorphic Computing platforms have recently achieved remarkable performance running more bio-realistic Spiking Neural Networks at high throughput and very low power consumption making them a natural alternative to ANNs. Here, we propose using the Random Neural Network (RNN), a spiking neural network with both theoretical and practical appealing properties, as a general purpose classifier that can match the classification power of ANNs on a number of tasks while enjoying all the features of a spiking neural network. This is demonstrated on a number of real-world classification datasets.