Abstract: A compute-in-memory neural network architecture combines neural circuits implemented in CMOS technology and synaptic conductance crossbar arrays. The crossbar memory structures store the weight parameters of the neural network in the conductances of the synapse elements, which define interconnects between lines of neurons of consecutive layers in the network at the crossbar intersection points.

Abstract: The multimodal query-driven imager provides efficient coding and streaming of visual information acquired directly on the focal plane. The query-driven approach to visual event coding uses clocked time-division multiplexing to continuously scan the array, querying each pixel for threshold change events in pixel intensity.

Abstract: Techniques for measuring on-chip component parameters are described herein. In one embodiment, a method for measuring one or more on-chip component parameters comprises measuring a time for an on-chip capacitor to charge to a voltage approximately equal to a reference voltage, and measuring a time for the on-chip capacitor to charge to a voltage approximately equal to a voltage across an on-chip component. The method also comprises determining a parameter of the on-chip component based on the measured time for the on-chip capacitor to charge to the voltage approximately equal to the reference voltage, the measured time for the on-chip capacitor to charge to the voltage approximately equal to the voltage across the on-chip component, and the reference voltage.