Unsupervised Regenerative Learning of Hierarchical Features in Spiking Deep Networks for Object Recognition
arXiv:1602.01510
Abstract
We present a spike-based unsupervised regenerative learning scheme to train Spiking Deep Networks (SpikeCNN) for object recognition problems using biologically realistic leaky integrate-and-fire neurons. The training methodology is based on the Auto-Encoder learning model wherein the hierarchical network is trained layer wise using the encoder-decoder principle. Regenerative learning uses spike-timing information and inherent latencies to update the weights and learn representative levels for each convolutional layer in an unsupervised manner. The features learnt from the final layer in the hierarchy are then fed to an output layer. The output layer is trained with supervision by showing a fraction of the labeled training dataset and performs the overall classification of the input. Our proposed methodology yields 0.92%/29.84% classification error on MNIST/CIFAR10 datasets which is comparable with state-of-the-art results. The proposed methodology also introduces sparsity in the hierarchical feature representations on account of event-based coding resulting in computationally efficient learning.
8 pages, 9 figures, <Under review in IJCNN 2016>
References in corpus (4)
- Improving neural networks by preventing co-adaptation of feature detectors
- OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Understanding Deep Image Representations by Inverting Them