Sapinet: A sparse event-based spatiotemporal oscillator for learning in the wild

TL;DR

Sapinet is a spike timing neural network designed for robust, one-shot learning in real-world scenarios, capable of handling noise and stimulus variations without extensive hyperparameter tuning.

Contribution

It introduces a novel event-based neural network that learns continuously without forgetting and requires minimal tuning, advancing real-world learning applications.

Findings

Achieved high classification accuracy on olfaction datasets

Effectively handled noise and stimulus similarity variations

Supported one-shot online learning without catastrophic forgetting

Abstract

We introduce Sapinet -- a spike timing (event)-based multilayer neural network for \textit{learning in the wild} -- that is: one-shot online learning of multiple inputs without catastrophic forgetting, and without the need for data-specific hyperparameter retuning. Key features of Sapinet include data regularization, model scaling, data classification, and denoising. The model also supports stimulus similarity mapping. We propose a systematic method to tune the network for performance. We studied the model performance on different levels of odor similarity, gaussian and impulse noise. Sapinet achieved high classification accuracies on standard machine olfaction datasets without the requirement of fine tuning for a specific dataset.