An Efficient Hardware Circuit for Spike Sorting Based on Competitive Learning Networks

Abstract

This study aims to present an effective VLSI circuit for multi-channel spike sorting. The circuit supports the spike detection, feature extraction and classification operations. The detection circuit is implemented in accordance with the nonlinear energy operator algorithm. Both the peak detection and area computation operations are adopted for the realization of the hardware architecture for feature extraction. The resulting feature vectors are classified by a circuit for competitive learning (CL) neural networks. The CL circuit supports both online training and classification. In the proposed architecture, all the channels share the same detection, feature extraction, learning and classification circuits for a low area cost hardware implementation. The clock-gating technique is also employed for reducing the power dissipation. To evaluate the performance of the architecture, an application-specific integrated circuit (ASIC) implementation is presented. Experimental results demonstrate that the proposed circuit exhibits the advantages of a low chip area, a low power dissipation and a high classification success rate for spike sorting.

Implementation of neurobiological and various signal processing algorithms using FPGA circuits

“…Dedicated systems based on Field-Programmable Gate Arrays (FPGAs) or Application-Specific Integrated Circuits (ASICs) are especially suited for this task because they are small, wearable and use insignificant amount of energy compared to traditional Central Processing Units (CPUs) or Graphics Processing Unit (GPUs). Using a dedicated system the computation time to process the vast amount of data from a multi-channel (high-dimensional) neural recording can be significantly reduced ( [41,42,43,44]). Although ASIC chips might be smaller and consume less power compared to FPGAs, which is advantageous in electrophysiological experiments with freely behaving animals where wireless technology is used to transfer neural data from the brain to the recording system [45], they usually lack flexibility for changes.…”