%Aigaion2 BibTeX export from Idiap Publications
%Saturday 07 November 2026 03:05:36 PM

@INPROCEEDINGS{Abdennadher_ICONS_2026,
                      author = {Abdennadher, Yesmine and Garner, Philip N.},
                    projects = {Idiap},
         mainresearchprogram = {Human-AI Teaming},
                       month = aug,
                       title = {Practical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape Smoothing},
                   booktitle = {ICONS '26: Proceedings of the International Conference on Neuromorphic Systems},
                        year = {2026},
                    location = {Chicago, IL, USA},
                         doi = {10.1145/3822454.3822477},
                    abstract = {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 predic-
tive 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 Com-
mands 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. Fur-
thermore, 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.},
                         pdf = {https://publications.idiap.ch/attachments/papers/2026/Abdennadher_ICONS_2026.pdf}
}