Adaptive conversion of real-valued input into spike trains
This addresses a bottleneck in spiking neural networks for real-time applications by reducing computational overhead and eliminating pre-processing needs, though it appears incremental as it builds on existing conversion methods.
The paper tackles the problem of converting real-valued input into spike trains for spiking neural networks by proposing a biologically plausible method that adapts to input statistics, enabling processing of raw, non-normalized streaming data with only one input neuron per variable instead of a population.
This paper presents a biologically plausible method for converting real-valued input into spike trains for processing with spiking neural networks. The proposed method mimics the adaptive behaviour of retinal ganglion cells and allows input neurons to adapt their response to changes in the statistics of the input. Thus, rather than passively receiving values and forwarding them to the hidden and output layers, the input layer acts as a self-regulating filter which emphasises deviations from the average while allowing the input neurons to become effectively desensitised to the average itself. Another merit of the proposed method is that it requires only one input neuron per variable, rather than an entire population of neurons as in the case of the commonly used conversion method based on Gaussian receptive fields. In addition, since the statistics of the input emerge naturally over time, it becomes unnecessary to pre-process the data before feeding it to the network. This enables spiking neural networks to process raw, non-normalised streaming data. A proof-of-concept experiment is performed to demonstrate that the proposed method operates as expected.