Active memristor based spiking neuromorphic circuit for motion detection

Abstract

A motion-sensing circuit for determining a direction of motion and a velocity of an object includes a first photo-receptor for sensing the object, an excitatory active memristor neuron circuit coupled to the first photo-receptor, a second photo-receptor for sensing the object, an inhibitory active memristor neuron circuit coupled to the second photo-receptor, and a self-excitatory active memristor output-counter neuron circuit coupled to the excitatory active memristor neuron circuit and coupled to the inhibitory active memristor neuron circuit.

Description

[0001] 【CROSS-REFERENCE TO RELATED APPLICATIONS】 [0002] This application is related to and claims priority to U.S. Provisional Application No. 62 / 838,671, filed 4 / 25 / 2019, and to U.S. Patent Application No. 15 / 976,687, filed 5 / 10 / 2018, which are hereby incorporated by reference , as fully elaborated. This application is also related to and claims priority to US Nonprovisional Patent Application Serial No. 16 / 793,387 filed 2 / 18 / 2020, which was concurrently filed, and which application is hereby incorporated by reference as if fully set forth. [0003] 【Statement Regarding Federal Funding】 [0004] none 【Technical field】 [0005] This disclosure relates to neural networks. 【Background technique】 [0006] In the animal retina, as shown in Figure 1, direction-selective (DS) ganglion cells respond strongly to movement in their preferred direction, but show minimal response to movement in the opposite (ineffective) direction. [0007] Figure 1 shows a functional neural circu...

AI Technical Summary

Problems solved by technology

The FS algorithm is better in this sense, but the slowly decaying boost pulse is still not energy friendly

The CMOS circuits involved in its design (see Fig. 2, Fig. 3, Fig. 4 in Ref. [6]) are relatively simple, so scalability is not such a concern

Images