Neuro-inspired speech recognition with recurrent spiking neurons

This paper investigates the potential of recurrent spiking neurons for classification problems. It presents a hybrid approach based on the paradigm of Reservoir Computing. The practical applications based on recurrent spiking neurons are limited due to their non-trivial learning algorithms. In the paradigm of Reservoir Computing, instead of training the whole recurrent network only the output layer (known as readout neurons) are trained. These recurrent neural networks are termed as microcircuits which are viewed as basic computational units in cortical computation. These microcircuits are connected as columns which are linked with other neighboring columns in cortical areas. These columns read out information from each other and can serve both as reservoir and readout. The design space for this paradigm is split into three domains; front end, reservoir, and back end. This work contributes to the identification of suitable front and back end processing techniques along with stable and compact reservoir dynamics, which provides a reliable framework for classification related problems.