Unsupervised regenerative learning of hierarchical features in Spiking Deep Networks for object recognition
Authors:
- 1 July 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 299-306
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 0.95%/24.58% 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.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Mapping from Frame-Driven to Frame-Free Event-Driven Vision Systems by Low-Rate Rate Coding and Coincidence Processing--Application to Feedforward ConvNetsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Real-time classification and sensor fusion with a spiking deep belief networkFrontiers in Neuroscience, 2013
- Unsupervised learning of hierarchical representations with convolutional deep belief networksCommunications of the ACM, 2011
- Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition2010
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- On the computational power of circuits of spiking neuronsJournal of Computer and System Sciences, 2004
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in positionBiological Cybernetics, 1980