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

Sanaullah Sanaullah
Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}), PMLR 233:220-227, 2024.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v233-sanaullah24a, title = {A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models}, author = {Sanaullah, Sanaullah}, booktitle = {Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL})}, pages = {220--227}, year = {2024}, editor = {Lutchyn, Tetiana and Ramírez Rivera, Adín and Ricaud, Benjamin}, volume = {233}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jan}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v233/sanaullah24a/sanaullah24a.pdf}, url = {https://proceedings.mlr.press/v233/sanaullah24a.html}, 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.} }
Endnote
%0 Conference Paper %T A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models %A Sanaullah Sanaullah %B Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}) %C Proceedings of Machine Learning Research %D 2024 %E Tetiana Lutchyn %E Adín Ramírez Rivera %E Benjamin Ricaud %F pmlr-v233-sanaullah24a %I PMLR %P 220--227 %U https://proceedings.mlr.press/v233/sanaullah24a.html %V 233 %X 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.
APA
Sanaullah, S.. (2024). A Hybrid Spiking-Convolutional Neural Network Approach for Advancing Machine Learning Models. Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}), in Proceedings of Machine Learning Research 233:220-227 Available from https://proceedings.mlr.press/v233/sanaullah24a.html.

Related Material