Log In Sign Up

Improving STDP-based Visual Feature Learning with Whitening

by   Pierre Falez, et al.

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). SNN 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 is detrimental to 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 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 fairly stable across datasets, making it possible to learn a single whitening transformation to process different datasets.


page 1

page 3

page 5

page 7


Deep Learning in Spiking Phasor Neural Networks

Spiking Neural Networks (SNNs) have attracted the attention of the deep ...

What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance

There is active research targeting local image manipulations that can fo...

Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation

Spiking Neural Networks (SNNs) operate with asynchronous discrete events...

Training Spiking Neural Networks with Local Tandem Learning

Spiking neural networks (SNNs) are shown to be more biologically plausib...

On the Transferability of Winning Tickets in Non-Natural Image Datasets

We study the generalization properties of pruned neural networks that ar...