Memristor-based neuroelectronics for artificial and hybrid intelligence
summary
Claims practical memristor prototypes that implement analog vector–matrix multiply in a 4-kbit crossbar, demonstrate precise multilevel resistive tuning and stochastic dynamics, and run inference on an Arduino extension board with open-source Python code. Shows proof-of-concept neural-processor cores and crossbar arrays that reduce energy per operation, interfaces that classify bioelectrical responses from neural cultures in real time, and closed-loop invasive and noninvasive setups that adapt stimulation based on memristor-processed signals.
AI-written summary · about
chapters (11)
- 0:00Memristor-based neuroelectronics intro
- 2:07Memristor definition
- 4:24Neuromorphic computing
- 6:59Advantages of memristor processors
- 8:22Hybrid electronic-biological systems
- 10:36Memristive effects mechanisms
- 13:38Memristor fabrication and testing
- 15:10Neural processor applications
- 16:12Neural interfaces and signals
- 19:05Biological signal processing
- 20:43Future perspectives
related talks
01h 57mIntroduction to Neuromorphic Computing
41mBrain-inspired computational primitives for reliable neuromorphic intelligence
43mKeeping Moore's law alive: Neuromorphic computing
01h 05mReal In-Memory Processing
37mHodgkin-Huxley, Memristors, and Edge of Chaos
43mThe Biological Path Towards Strong AI
01h 16mRethinking Computing with Neuro-Inspired Learning: Algorithms to Hardware
42mOn the Link Between Energy & Information for the Design of Neuromorphic Systems