PUBLIKATIONSSERVER

A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models

S. Sanaullah, K. Roy, U. Rückert, T. Jungeblut, in: T. Lutchyn, A. Ramírez Rivera, B. Ricaud (Eds.), Proceedings of the 5th Northern Lights Deep Learning Conference, Proceedings of Machine Learning Research (PMLR), UiT The Arctic University, Tromsø, Norway, 2024.

Konferenzbeitrag | Veröffentlicht | Englisch
Autor*in
Sanaullah, SanaullahFH Bielefeld ; Roy, Kaushik; Rückert, Ulrich ; Jungeblut, ThorstenFH Bielefeld
Herausgeber*in
Lutchyn, Tetiana ; Ramírez Rivera, Adín ; Ricaud, Benjamin
Abstract
In this article, we propose a novel standalone hybrid Spiking-Convolutional Neural Network (SC-NN) model and test on using image inpainting tasks. Our approach uses the unique capabilities of SNNs, such as event-based computation and temporal processing, along with the strong representation learning abilities of CNNs, to generate high-quality inpainted images. The model is trained on a custom dataset specifically designed for image inpainting, where missing regions are created using masks. The hybrid model consists of SNNConv2d layers and traditional CNN layers. The SNNConv2d layers implement the leaky integrate-and-fire (LIF) neuron model, capturing spiking behavior, while the CNN layers capture spatial features. In this study, a mean squared error (MSE) loss function demonstrates the training process, where a training loss value of 0.015, indicates accurate performance on the training set and the model achieved a validation loss value as low as 0.0017 on the testing set. Furthermore, extensive experimental results demonstrate state-of-the-art performance, showcasing the potential of integrating temporal dynamics and feature extraction in a single network for image inpainting.
Erscheinungsjahr
Titel des Konferenzbandes
Proceedings of the 5th Northern Lights Deep Learning Conference
Band
233
Konferenz
5th Northern Lights Deep Learning Conference NLDL
Konferenzort
UiT The Arctic University, Tromsø, Norway
Konferenzdatum
2024-01-09 – 2024-01-11
FH-PUB-ID

Zitieren

Sanaullah, Sanaullah ; Roy, Kaushik ; Rückert, Ulrich ; Jungeblut, Thorsten: A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models. In: Lutchyn, T. ; Ramírez Rivera, A. ; Ricaud, B. (Hrsg.): Proceedings of the 5th Northern Lights Deep Learning Conference. Bd. 233. UiT The Arctic University, Tromsø, Norway : Proceedings of Machine Learning Research (PMLR), 2024
Sanaullah S, Roy K, Rückert U, Jungeblut T. A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models. In: Lutchyn T, Ramírez Rivera A, Ricaud B, eds. Proceedings of the 5th Northern Lights Deep Learning Conference. Vol 233. UiT The Arctic University, Tromsø, Norway: Proceedings of Machine Learning Research (PMLR); 2024. doi:10.48550/arXiv.2407.08861
Sanaullah, S., Roy, K., Rückert, U., & Jungeblut, T. (2024). A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models. In T. Lutchyn, A. Ramírez Rivera, & B. Ricaud (Eds.), Proceedings of the 5th Northern Lights Deep Learning Conference (Vol. 233). UiT The Arctic University, Tromsø, Norway: Proceedings of Machine Learning Research (PMLR). https://doi.org/10.48550/arXiv.2407.08861
@inproceedings{Sanaullah_Roy_Rückert_Jungeblut_2024, place={UiT The Arctic University, Tromsø, Norway}, title={A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models}, volume={233}, DOI={10.48550/arXiv.2407.08861}, booktitle={Proceedings of the 5th Northern Lights Deep Learning Conference}, publisher={Proceedings of Machine Learning Research (PMLR)}, author={Sanaullah, Sanaullah and Roy, Kaushik and Rückert, Ulrich and Jungeblut, Thorsten}, editor={Lutchyn, Tetiana and Ramírez Rivera, Adín and Ricaud, Benjamin Editors}, year={2024} }
Sanaullah, Sanaullah, Kaushik Roy, Ulrich Rückert, and Thorsten Jungeblut. “A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models.” In Proceedings of the 5th Northern Lights Deep Learning Conference, edited by Tetiana Lutchyn, Adín Ramírez Rivera, and Benjamin Ricaud, Vol. 233. UiT The Arctic University, Tromsø, Norway: Proceedings of Machine Learning Research (PMLR), 2024. https://doi.org/10.48550/arXiv.2407.08861.
S. Sanaullah, K. Roy, U. Rückert, and T. Jungeblut, “A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models,” in Proceedings of the 5th Northern Lights Deep Learning Conference, UiT The Arctic University, Tromsø, Norway, 2024, vol. 233.
Sanaullah, Sanaullah, et al. “A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models.” Proceedings of the 5th Northern Lights Deep Learning Conference, edited by Tetiana Lutchyn et al., vol. 233, Proceedings of Machine Learning Research (PMLR), 2024, doi:10.48550/arXiv.2407.08861.

Link(s) zu Volltext(en)
Access Level
Restricted Closed Access
Externes Material:
Bestätigungsschreiben

Export

Markierte Publikationen

Open Data LibreCat

Web of Science

Dieser Datensatz im Web of Science®

Quellen

arXiv arXiv:2407.08861

Suchen in

Google Scholar