Improving the Multimodal Classification Performance of Spiking Neural Networks Through Hyper-Parameter Optimization

Spiking Neural Networks (SNNs) are computational models that emulate the spike-based communication found in biological neural networks. These models are increasingly recognized for their potential to process sensor data in a biologically analogous manner, particularly within multimodal contexts involving both image and audio data. Nonetheless, optimizing the classification performance of deep SNNs is a complex task, frequently impeded by the intricate interactions of hyper-parameters. This paper addresses this challenge by employing advanced hyper-parameter optimization techniques to enhance the classification efficacy of a multimodal SNN. Our work not only refines the performance of SNNs on heterogeneous data types but also elucidates the intricate dynamics between hyper-parameter configurations and classification accuracy within these networks.