摘要 |
The present invention involves the use of temporal or spatio-/spectro temporal data (SSTD) for an early classification of outputs that are results of spatio-temporal patterns of data. Classification models according to preferred embodiments are based on spiking neural networks (SNN), suitable to learn and classify SSTD. The invention can be used to predict early events in many applications, for example engineering, bioinformatics, neuroinformatics, predicting response to treatment of neurological and brain disease, ecology, environment, medicine, and economics, among others. Preferred embodiments of the present invention involve a method and system for personalised modelling of SSTD and early prediction of events. The method and system are based on an evolving spiking neural network reservoir architecture (eSNNr). The system comprises: a spike-time encoding module to encode continuous value input information into spike trains, a recurrent 3D SNNr and an eSNN as an output classification module. |