Reconstruction, Identification and Implementation Methods for Spiking Neural Circuits

Abstract

To my family iii The third problem addressed in this work is given by the need of developing neuromorphic engineering circuits that perform mathematical computations in the spike domain.In this respect, this thesis developed a new representation between the time encoded input and output of a linear filter, where the TEM is represented by an ideal IF neuron. A new practical algorithm is developed based on this representation. The proposed algorithm is significantly faster than the alternative approach, which involves reconstructing the input, simulating the linear filter, and subsequently encoding the resulting output into a spike train.

Learning with Precise Spike Times: A New Decoding Algorithm for Liquid State Machines

“…In recent years, a lot of research effort has been expanded to establish a sound theoretical basis for encoding and decoding using the precise timing of the spikes rather than spike-count rates (Lazar & Pnevmatikakis, 2008;Florescu & Coca, 2015;Lazar & Slutskiy, 2015;Florescu, 2017;Florescu & Coca, 2018). A range of supervised learning approaches that utilise temporal coding schemes have been developed for recurrent spiking neural networks (SNNs) with feedforward and feedback connections (Gardner & Grüning, 2016;Gütig, 2014).…”