Abstract
This paper proposes a new method for an optimized mapping of temporal variables, describing a temporal stream data, into the recently proposed NeuCube spiking neural network architecture. This optimized mapping extends the use of the NeuCube, which was initially designed for spatio-temporal brain data [1, 2], to work on arbitrary stream data and to achieve a better accuracy of temporal pattern recognition, a better and earlier event prediction and a better understanding of complex temporal stream data through visualization of the NeuCube connectivity. NeuCube consists of input encoding module, that transforms continuous value temporal data into spike trains, a recurrent 3D spiking neural network cube, and a dynamic evolving spiking neural network as a classifier or a regressor. The effect of the new mapping is demonstrated on three bench mark problems. The first one is early prediction of patient sleep stage event from temporal physiological data. The second one is pattern recognition of dynamic temporal patterns of traffic in the Bay Area of California and the last one is the Challenge 2012 contest data set. In all cases the use of the proposed mapping leads to an improved accuracy of pattern recognition and event prediction and a better understanding of the data when compared to traditional machine learning techniques or spiking neural network reservoirs with arbitrary mapping of the variables.
Original language | English |
---|---|
Pages (from-to) | 1305-1317 |
Number of pages | 13 |
Journal | IEEE Transactions on Neural Networks and Learning Systems |
Volume | 28 |
Issue number | 6 |
Early online date | 15 Mar 2016 |
DOIs | |
Publication status | Published (in print/issue) - 1 Jun 2017 |
Keywords
- early event prediction
- NeuCube architecture
- spatiotemporal data
- spiking neural networks