Nonlinear Cognitive Signal Processing in Ultralow-Power Programmable Analog Hardware
This brief presents a programmable ultralow-power analog neural signal processing system. The analog hardware implements a nonlinear model that can replicate and predict, in real time, the temporal neural codes used in complex brain functions. The transistors of the analog circuits operate in weak inversion. A digital control system is used to program model parameters and calibrate mismatches.
The chip was implemented in a 130-nm complementary metal-oxide-semiconductor technology and occupies an area of 1 mm2. The power consumption of the system is 120 nW. The modular design allows for easy scaling to achieve large-scale hardware systems that emulate spike transformations of populations of neurons.