Improving STDP-based Visual Feature Learning with Whitening
| Autor: | Ioan Marius Bilasco, Pierre Falez, Pierre Tirilly |
|---|---|
| Přispěvatelé: | Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Université de Lille, FOX MIIRE (LIFL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Ecole nationale supérieure Mines-Télécom Lille Douai (IMT Lille Douai), Institut Mines-Télécom [Paris] (IMT) |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) Feature extraction Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Machine Learning (cs.LG) 03 medical and health sciences 0302 clinical medicine 0202 electrical engineering electronic engineering information engineering Neural and Evolutionary Computing (cs.NE) ComputingMilieux_MISCELLANEOUS Spiking neural network Artificial neural network Contextual image classification business.industry Computer Science - Neural and Evolutionary Computing [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Pattern recognition Unsupervised learning 020201 artificial intelligence & image processing Artificial intelligence business Feature learning 030217 neurology & neurosurgery MNIST database |
| Zdroj: | IJCNN IJCNN 2020-International Joint Conference on Neural Networks IJCNN 2020-International Joint Conference on Neural Networks, Jul 2020, Glasgow, United Kingdom |
| DOI: | 10.1109/ijcnn48605.2020.9207373 |
| Popis: | In recent years, spiking neural networks (SNNs) emerge as an alternative to deep neural networks (DNNs). SNNs present a higher computational efficiency – using low-power neuromorphic hardware – and require less labeled data for training – using local and unsupervised learning rules such as spike timing-dependent plasticity (STDP). SNNs have proven their effectiveness in image classification on simple datasets such as MNIST. However, to process natural images, a pre-processing step is required. Difference-of-Gaussians (DoG) filtering is typically used together with on-center / off-center coding, but it results in a loss of information that decreases the classification performance. In this paper, we propose to use whitening as a pre-processing step before learning features with STDP. Experiments on CIFAR-10 show that whitening allows STDP to learn visual features that are visually closer to the ones learned with standard neural networks, with a significantly increased classification performance as compared to DoG filtering. We also propose an approximation of whitening as convolution kernels that is computationally cheaper to learn and more suited to be implemented on neuromorphic hardware. Experiments on CIFAR-10 show that it performs similarly to regular whitening. Cross-dataset experiments on CIFAR-10 and STL-10 also show that it is stable across datasets, making it possible to learn a single whitening transformation to process different datasets. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|