A 128-Channel Extreme Learning Machine-Based Neural Decoder for Brain Machine Interfaces

Abstract

In the paper we discuss about the extreme learning machine (ELM) interface which has potential to restore the lost sensorimotor functions in people. The key element used in brainmachine interface (BMI) is neural decoder. Extreme learning machine interface controls the external devices by modulating their neural activity. A mathematical algorithm is introduced to record the neural activity in extreme learning machine interface. The proposed system utilizes a decoder to initialize the feedback approach.  A motor ELM is modelled as closed loop control system, where the controller is brain. At last the proposed system takes limited number of input channels and reduces the number of programmable weights.