An Adaptive Intelligent System Based on Energy‐Efficient Synaptic Resistor Circuits with Fast Real‐Time Learning
Abstract
Unlike the human brain, which concurrently executes inference and learning algorithms in neural networks in real time, artificial intelligence (AI) systems usually execute inference algorithms and learning algorithms in series, which lack fast real‐time learning functionality, high computing energy efficiency, and adaptability in the complex, erratic real world. Herein, an intelligent system integrating a drone and a synaptic resistor (synstor) circuit that concurrently executes inference and reinforcement learning algorithms in real‐time is reported. Without any prior learning or programming, the conductance matrix of the synstor circuit is dynamically optimized in its real‐time learning processes, thus enabling the drone to adapt and fly toward its target positions in erratic aerodynamic environments. In learning experiments involving a drone driven by synstor circuits, humans, or computers, the real‐time learning by the synstor circuit is superior to the real‐time learning by humans and the cloud learning by computers, in terms of key benchmarks including adaptability, learning time, precision, power consumption, and energy efficiency. By circumventing the fundamental limitations in computers, synstor circuits open up new directions to establish AI systems with brain‐like fast real‐time learning functionality, high computing energy efficiency, and adaptability in complex, erratic real‐world environments for versatile applications.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Aug 05, 2022
- Source ID
- 10.1002/aisy.202200105
Entities
People
- Andrew Tudor
- Atharva Deo
- Bharathwaj Suresh
- Cameron D. Danesh
- Christopher M. Shaffer
- Dhruva Nathan
- Rahul Shenoy
- Yong Chen
- Zixuan Rong
Organizations
- Air Force Office of Scientific Research
- University of California, Los Angeles