Practical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape Smoothing
This work addresses the challenge of uncertainty and loss-landscape smoothing in SNNs for speech processing, representing an incremental improvement over existing methods.
The paper tackled the irregular predictive landscape in Spiking Neural Networks (SNNs) for speech processing by applying Bayesian inference, resulting in improved performance metrics like negative log-likelihood and Brier score on datasets such as Heidelberg Digits and Speech Commands.
Spiking Neural Networks (SNNs) are naturally suited for speech processing tasks due to their specific dynamics, which allows them to handle temporal data. However, the threshold-based generation of spikes in SNNs intuitively causes an angular or irregular predictive landscape. We explore the effect of using the Bayesian learning approach for the weights on the irregular predictive landscape. For the surrogate-gradient SNNs, we also explore the application of the Improved Variational Online Newton (IVON) approach, which is an efficient variational approach. The performance of the proposed approach is evaluated on the Heidelberg Digits and Speech Commands datasets. The hypothesis is that the Bayesian approach will result in a smoother and more regular predictive landscape, given the angular nature of the deterministic predictive landscape. The experimental evaluation of the proposed approach shows improved performance on the negative log-likelihood and Brier score. Furthermore, the proposed approach has resulted in a smoother and more regular predictive landscape compared to the deterministic approach, based on the one-dimensional slices of the weight space