The Yin-Yang dataset

TL;DR

The Yin-Yang dataset is a compact, versatile dataset designed for research on biologically plausible error backpropagation and deep learning in spiking neural networks, facilitating early-stage prototyping and exploration.

Contribution

It introduces a new dataset tailored for spiking neural networks, emphasizing simplicity, transferability, and clear depth-related accuracy gaps for research and development.

Findings

Smaller and faster to learn than classic datasets

Shows a clear accuracy gap between shallow and deep networks

Easily transferable between spatial and temporal domains

Abstract

The Yin-Yang dataset was developed for research on biologically plausible error backpropagation and deep learning in spiking neural networks. It serves as an alternative to classic deep learning datasets, especially in early-stage prototyping scenarios for both network models and hardware platforms, for which it provides several advantages. First, it is smaller and therefore faster to learn, thereby being better suited for small-scale exploratory studies in both software simulations and hardware prototypes. Second, it exhibits a very clear gap between the accuracies achievable using shallow as compared to deep neural networks. Third, it is easily transferable between spatial and temporal input domains, making it interesting for different types of classification scenarios.