A Neural Spiking Approach Compared to Deep Feedforward Networks on Stepwise Pixel Erasement

Autor:	Larisch, René, Teichmann, Michael, Hamker, Fred H.
Rok vydání:	2019
Předmět:	Computer Science - Machine Learning Computer Science - Computer Vision and Pattern Recognition Computer Science - Neural and Evolutionary Computing Statistics - Machine Learning
Druh dokumentu:	Working Paper
DOI:	10.1007/978-3-030-01418-6_25
Popis:	In real world scenarios, objects are often partially occluded. This requires a robustness for object recognition against these perturbations. Convolutional networks have shown good performances in classification tasks. The learned convolutional filters seem similar to receptive fields of simple cells found in the primary visual cortex. Alternatively, spiking neural networks are more biological plausible. We developed a two layer spiking network, trained on natural scenes with a biologically plausible learning rule. It is compared to two deep convolutional neural networks using a classification task of stepwise pixel erasement on MNIST. In comparison to these networks the spiking approach achieves good accuracy and robustness. Comment: Published in ICANN 2018: Artificial Neural Networks and Machine Learning - ICANN 2018 https://link.springer.com/chapter/10.1007/978-3-030-01418-6_25 The final authenticated publication is available online at https://doi.org/10.1007/978-3-030-01418-6_25
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1912.03201 Zobrazit plný text záznamu View this record from Arxiv