Unsupervised Regenerative Learning of Hierarchical Features in Spiking Deep Networks for Object Recognition
This work addresses object recognition problems for applications in neuromorphic computing, but it is incremental as it builds on existing Auto-Encoder and spiking network methods.
The paper tackles object recognition by training Spiking Deep Networks with an unsupervised regenerative learning scheme, achieving classification errors of 0.92% on MNIST and 29.84% on CIFAR10, which are comparable to state-of-the-art results.
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.