Fazhan Liu
Papers
1
Total Citations
14
H-Index
1
About
Driven by a fascination with how biological learning mechanisms can inspire artificial intelligence, Fazhan Liu has carved a distinctive niche at the intersection of neuromorphic computing and cognitive modeling. His research primarily focuses on designing memristive neural network circuits that emulate complex psychological processes, most notably operant conditioning—the fundamental reinforcement learning mechanism that governs how organisms adapt behavior based on rewards and punishments. Liu’s landmark 2023 paper, “Memristive Neural Network Circuit of Operant Conditioning With Reward Delay and Variable Punishment Intensity,” has already garnered 14 citations, demonstrating its immediate impact on the field. In this work, he introduced a non-volatile memristor-based circuit capable of mimicking nuanced learning behaviors, including the effects of delayed rewards and adjustable punishment intensity—a significant step toward more biologically realistic artificial learning systems. By bridging neuroscience, psychology, and circuit design, Liu’s contributions offer a hardware-friendly pathway for implementing adaptive, context-aware AI. His work stands out for its elegant integration of theoretical principles with practical circuit implementation, making him a rising voice in the quest to build machines that learn like living organisms.
Research Focus
Key Achievements
Top Papers
- 1