One step Backpropagation Through Time for learning input mapping in reservoir computing applied to speech recognition

Recurrent neural networks are very powerful engines for processing information that is coded in time, however, many problems with common training algorithms, such as Backpropagation Through Time, remain. Because of this, another important learning setup known as Reservoir Computing has appeared in recent years, where one uses an essentially untrained network to perform computations. Though very successful in many applications, using a random network can be quite inefficient when considering the required number of neurons and the associated computational costs. In this paper we introduce a highly simplified version of Backpropagation Through Time by basically truncating the error backpropagation to one step back in time, and we combine this with the classic Reservoir Computing setup using an instantaneous linear readout. We apply this setup to a spoken digit recognition task and show it to give very good results for small networks.