{"main_file_link":[{"open_access":"1","url":"https://openreview.net/forum?id=0YiM1yOSUq"}],"type":"conference","conference":{"start_date":"2024-01-09","end_date":"2024-01-11","name":"5th Northern Lights Deep Learning Conference NLDL","location":"UiT The Arctic University, Tromsø, Norway"},"abstract":[{"text":"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.","lang":"eng"}],"place":"UiT The Arctic University, Tromsø, Norway","date_updated":"2024-07-22T14:54:41Z","language":[{"iso":"eng"}],"intvolume":"       233","oa":"1","editor":[{"first_name":"Tetiana ","last_name":"Lutchyn","full_name":"Lutchyn, Tetiana "},{"last_name":"Ramírez Rivera","full_name":"Ramírez Rivera, Adín ","first_name":"Adín "},{"first_name":"Benjamin ","last_name":"Ricaud","full_name":"Ricaud, Benjamin "}],"external_id":{"isi":["https://openreview.net/forum?id=0YiM1yOSUq"],"arxiv":["arXiv:2407.08861"]},"publisher":"Proceedings of Machine Learning Research (PMLR)","author":[{"orcid":"0000-0003-4112-802X","first_name":"Sanaullah","id":"248865","full_name":"Sanaullah, Sanaullah","last_name":"Sanaullah","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0003-4112-802X/work/163028077"},{"first_name":"Kaushik","last_name":"Roy","full_name":"Roy, Kaushik"},{"full_name":"Rückert, Ulrich ","last_name":"Rückert","first_name":"Ulrich "},{"full_name":"Jungeblut, Thorsten","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0001-7425-8766/work/163028078","last_name":"Jungeblut","orcid":"0000-0001-7425-8766","first_name":"Thorsten","id":"242294"}],"doi":"10.48550/arXiv.2407.08861","volume":233,"quality_controlled":"1","project":[{"name":"Institut für Systemdynamik und Mechatronik","_id":"beb248c8-cd75-11ed-b77c-e432b4711f7b"}],"title":"A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models","date_created":"2024-07-05T10:19:09Z","publication":"Proceedings of the 5th Northern Lights Deep Learning Conference","citation":{"ama":"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. <i>Proceedings of the 5th Northern Lights Deep Learning Conference</i>. Vol 233. UiT The Arctic University, Tromsø, Norway: Proceedings of Machine Learning Research (PMLR); 2024. doi:<a href=\"https://doi.org/10.48550/arXiv.2407.08861\">10.48550/arXiv.2407.08861</a>","mla":"Sanaullah, Sanaullah, et al. “A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models.” <i>Proceedings of the 5th Northern Lights Deep Learning Conference</i>, edited by Tetiana  Lutchyn et al., vol. 233, Proceedings of Machine Learning Research (PMLR), 2024, doi:<a href=\"https://doi.org/10.48550/arXiv.2407.08861\">10.48550/arXiv.2407.08861</a>.","bibtex":"@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={<a href=\"https://doi.org/10.48550/arXiv.2407.08861\">10.48550/arXiv.2407.08861</a>}, 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} }","ieee":"S. Sanaullah, K. Roy, U. Rückert, and T. Jungeblut, “A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models,” in <i>Proceedings of the 5th Northern Lights Deep Learning Conference</i>, UiT The Arctic University, Tromsø, Norway, 2024, vol. 233.","chicago":"Sanaullah, Sanaullah, Kaushik Roy, Ulrich  Rückert, and Thorsten Jungeblut. “A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models.” In <i>Proceedings of the 5th Northern Lights Deep Learning Conference</i>, 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. <a href=\"https://doi.org/10.48550/arXiv.2407.08861\">https://doi.org/10.48550/arXiv.2407.08861</a>.","apa":"Sanaullah, S., Roy, K., Rückert, U., &#38; Jungeblut, T. (2024). A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models. In T. Lutchyn, A. Ramírez Rivera, &#38; B. Ricaud (Eds.), <i>Proceedings of the 5th Northern Lights Deep Learning Conference</i> (Vol. 233). UiT The Arctic University, Tromsø, Norway: Proceedings of Machine Learning Research (PMLR). <a href=\"https://doi.org/10.48550/arXiv.2407.08861\">https://doi.org/10.48550/arXiv.2407.08861</a>","alphadin":"<span style=\"font-variant:small-caps;\">Sanaullah, Sanaullah</span> ; <span style=\"font-variant:small-caps;\">Roy, Kaushik</span> ; <span style=\"font-variant:small-caps;\">Rückert, Ulrich </span> ; <span style=\"font-variant:small-caps;\">Jungeblut, Thorsten</span>: A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models. In: <span style=\"font-variant:small-caps;\">Lutchyn, T.</span> ; <span style=\"font-variant:small-caps;\">Ramírez Rivera, A.</span> ; <span style=\"font-variant:small-caps;\">Ricaud, B.</span> (Hrsg.): <i>Proceedings of the 5th Northern Lights Deep Learning Conference</i>. Bd. 233. UiT The Arctic University, Tromsø, Norway : Proceedings of Machine Learning Research (PMLR), 2024","short":"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."},"user_id":"220548","_id":"4783","status":"public","publication_status":"published","related_material":{"link":[{"url":"https://openreview.net/forum?id=0YiM1yOSUq","relation":"confirmation"}]},"year":"2024"}