Adaptive Input-to-Neuron Interlink Development in Training of Spike-Based Liquid State Machines

In this paper, we present a novel approach in developing input-to-neuron interlinks to achieve better accuracy in spike-based liquid state machines. An energy-efficient Spiking Neural Network suffer from lower accuracy in image classification compared to deep learning models. The previous LSM models randomly connect input neurons to excitatory neurons in a liquid. This limits the expressive power of a liquid model as large portion of excitatory neurons become inactive which never fire. To overcome this limitation, we propose an adaptive interlink development method which achieves 3.2% higher classification accuracy than the static LSM model of 3,200 neurons. Also, our hardware implementation on FPGA improves performance by 3.16~4.99 x or 1.47~3.95× over CPU/GPU.