An event-based classifier for Dynamic Vision Sensor and synthetic data
Serrano Gotarredona, María Teresa
Linares Barranco, Bernabé
|Department||Universidad de Sevilla. Departamento de Arquitectura y Tecnología de Computadores|
|Published in||Frontiers in Neuroscience, 11 (artículo 360)|
|Abstract||This paper introduces a novel methodology for training an event-driven classifier within
a Spiking Neural Network (SNN) System capable of yielding good classification results
when using both synthetic input data and real ...
This paper introduces a novel methodology for training an event-driven classifier within a Spiking Neural Network (SNN) System capable of yielding good classification results when using both synthetic input data and real data captured from Dynamic Vision Sensor (DVS) chips. The proposed supervised method uses the spiking activity provided by an arbitrary topology of prior SNN layers to build histograms and train the classifier in the frame domain using the stochastic gradient descent algorithm. In addition, this approach can cope with leaky integrate-and-fire neuron models within the SNN, a desirable feature for real-world SNN applications, where neural activation must fade away after some time in the absence of inputs. Consequently, this way of building histograms captures the dynamics of spikes immediately before the classifier. We tested our method on the MNIST data set using different synthetic encodings and real DVS sensory data sets such as N-MNIST, MNIST-DVS, and Poker-DVS using the same network topology and feature maps. We demonstrate the effectiveness of our approach by achieving the highest classification accuracy reported on the N-MNIST (97.77%) and Poker-DVS (100%) real DVS data sets to date with a spiking convolutional network. Moreover, by using the proposed method we were able to retrain the output layer of a previously reported spiking neural network and increase its performance by 2%, suggesting that the proposed classifier can be used as the output layer in works where features are extracted using unsupervised spike-based learningmethods. In addition, we also analyze SNN performance figures such as total event activity and network latencies, which are relevant for eventual hardware implementations. In summary, the paper aggregates unsupervised-trained SNNs with a supervised-trained SNN classifier, combining and applying them to heterogeneous sets of benchmarks, both synthetic and from real DVS chips.
|Cite||Stromatias, E., Soto, M., Serrano Gotarredona, M.T. y Linares Barranco, B. (2017). An event-based classifier for Dynamic Vision Sensor and synthetic data. Frontiers in Neuroscience, 11 (artículo 360)|