Skimming Digits: Neuromorphic Classification of Spike-Encoded Images
By Gregory Cohen, Garrick Orchard, Sio-Hoi Leng, Jonathan C. Tapson, Ryad Benosman, A. van Schaik. 2016
56 citations recorded by the source corpus.
The growing demands placed upon the field of computer vision have renewed the focus on alternative visual scene representations and processing paradigms. Silicon retinea provide an alternative means of imaging the visual environment, and produce frame-free spatio-temporal data. This paper presents an investigation into event-based digit classification using N-MNIST, a neuromorphic dataset created with a silicon retina, and the Synaptic Kernel Inverse Method (SKIM), a learning method based on principles of dendritic computation. As this work represents the first large-scale and multi-class classification task performed using the SKIM network, it explores different training patterns and output determination methods necessary to extend the original SKIM method to support multi-class problems. Making use of SKIM networks applied to real-world datasets, implementing the largest hidden layer sizes and simultaneously training the largest number of output neurons, the classification system achieved a best-case accuracy of 92.87% for a network containing 10,000 hidden layer neurons. These results represent the highest accuracies achieved against the dataset to date and serve to validate the application of the SKIM method to event-based visual classification tasks. Additionally, the study found that using a square pulse as the supervisory training signal produced the highest accuracy for most output determination methods, but the results also demonstrate that an exponential pattern is better suited to hardware implementations as it makes use of the simplest output determination method based on the maximum value.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Daniel Neil
- Shih-Chii Liu
- Giacomo Indiveri
- Michael Pfeiffer
- Peter U. Diehl
- Hesham Mostafa
- Guillermo Gallego
- Ioana Bica
Citations in the corpus
- Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences (2016, background): “It is also worth noting that these results form a new state-of-the-art accuracy for this dataset [24, 7].”
- Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks (2017, unknown): “74% Spiking MLP(BP) [35] 34× 34× 2-10000-10 None 92.”