Location
Hilton Waikoloa Village, Hawaii
Event Website
https://hicss.hawaii.edu/
Start Date
7-1-2025 12:00 AM
End Date
10-1-2025 12:00 AM
Description
Timely and energy-efficient time series forecasting can play a key role on edge devices, where power requirements can be stringent. Spiking Neural Networks (SNNs) are regarded as a new avenue in which to solve time series problems, but with lower SWaP (Size, Weight, and Power) needs. We propose an SNN pipeline to process and forecast time series, developing a novel data spike-encoding mechanism and two loss functions that optimise the prediction of the upcoming spikes. Our approach encodes a signal into sequences of spikes that approximate its derivative, preparing the data to be processed by the SNN, while our proposed loss functions account for the reconstruction of the output spikes into a meaningful value to promote convergence to top-level solutions. Results show that our solution can effectively learn from the encoded data and the SNN trained with our loss function can outperform the same model trained with SLAYER's default loss.
Recommended Citation
Manna, Davide; Di Caterina, Gaetano; Vicente-Sola, Alex; and Kirkland, Paul, "An Approach to Time Series Forecasting With Derivative Spike Encoding and Spiking Neural Networks" (2025). Hawaii International Conference on System Sciences 2025 (HICSS-58). 3.
https://aisel.aisnet.org/hicss-58/st/edge_computing/3
An Approach to Time Series Forecasting With Derivative Spike Encoding and Spiking Neural Networks
Hilton Waikoloa Village, Hawaii
Timely and energy-efficient time series forecasting can play a key role on edge devices, where power requirements can be stringent. Spiking Neural Networks (SNNs) are regarded as a new avenue in which to solve time series problems, but with lower SWaP (Size, Weight, and Power) needs. We propose an SNN pipeline to process and forecast time series, developing a novel data spike-encoding mechanism and two loss functions that optimise the prediction of the upcoming spikes. Our approach encodes a signal into sequences of spikes that approximate its derivative, preparing the data to be processed by the SNN, while our proposed loss functions account for the reconstruction of the output spikes into a meaningful value to promote convergence to top-level solutions. Results show that our solution can effectively learn from the encoded data and the SNN trained with our loss function can outperform the same model trained with SLAYER's default loss.
https://aisel.aisnet.org/hicss-58/st/edge_computing/3