Synaptic Resistor Circuits Based on Al Oxide and Ti Silicide for Concurrent Learning and Signal Processing in Artificial Intelligence Systems. Issue 15 (28th February 2023)

• Record Type: Journal Article
• Authors: Gao, Dawei; Shenoy, Rahul; Yi, Suin; Lee, Jungmin; Xu, Mingjie; Rong, Zixuan; Deo, Atharva; Nathan, Dhruva; Zheng, Jian‐Guo; Williams, R. Stanley; Chen, Yong
• Is Part Of: Advanced materials. Volume 35:Issue 15(2023)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2023-02-28
• Subjects: Al oxide -- artificial intelligence systems -- concurrent learning and signal processing -- synaptic resistor circuits -- Ti silicide; Materials -- Periodicals; Chemical vapor deposition -- Periodicals; 620.11
• DOI: 10.1002/adma.202210484
• Languages: English
• ISSNs: 0935-9648

Abstract

Abstract: Neurobiological circuits containing synapses can process signals while learning concurrently in real time. Before an artificial neural network (ANN) can execute a signal‐processing program, it must first be programmed by humans or trained with respect to a large and defined data set during learning processes, resulting in significant latency, high power consumption, and poor adaptability to unpredictable changing environments. In this work, a crossbar circuit of synaptic resistors (synstors) is reported, each synstor integrating a Si channel with an Al oxide memory layer and Ti silicide Schottky contacts. Individual synstors are characterized and analyzed to understand their concurrent signal‐processing and learning abilities. Without any prior training, synstor circuits concurrently execute signal processing and learning in real time to fly drones toward a target position in an aerodynamically changing environment faster than human controllers, and with learning speed, performance, power consumption, and adaptability to the environment significantly superior to an ANN running on computers. The synstor circuit provides a path to establish power‐efficient intelligent systems with real‐time learning and adaptability in the capriciously mutable real world. Abstract : A synaptic resistor (synstor) circuit concurrently executes signal processing and learning in real time to fly drones toward a target in an aerodynamically changing environment faster than human controllers, and with learning speed, performance, power consumption, and adaptability to the environment significantly superior to an artificial neural network on computers, providing a path to establish power‐efficient intelligent systems in the capriciously mutable real world.