Lernende Memristoren lösen Navigationsaufgaben: «Das macht das System enorm schnell und effizient»
KI-Berechnungen auf herkömmlicher Hardware sind ineffizient und brauchen viel Energie. Nicht zuletzt deshalb wird vermehrt im Bereich des neuromorphen Rechnens geforscht, das sich am menschlichen…
Read the full articleYou might also wanna read
Memristor chips target faster, greener solutions to complex problems
Memristor-based chips could solve demanding optimization problems far faster and with less energy by replacing dense connections with compac
Shiitake Mushroom Mycelium Used to Create Sustainable Memristors for Neuromorphic Computing
Neuromorphic computing, inspired by the structure of the brain, offers advantages in parallel processing, memory storage, and energy efficie
journals.plos.org·8mo ago
SK hynix and TetraMem collaborate on experimental chip to bolster energy efficiency for edge AI devices — memristor-based in-memory SoC research leaves performance questions up in the air
SK hynix, TetraMem, and the University of Southern California built a memristor-based in-memory computing system-on-chip for AI edge devices
TetraMem, SK hynix Highlight Memristor-Based AI Computing SoC Collaboration
Joint research demonstrates analog in-memory computing SoC designed to improve AI inference efficiency by reducing data movement. The post T
AI with Cerebellum-like Functions: A New 'Memtransistor' for Efficient Computing
Researchers from Northwestern University have created a device inspired by the cerebellum's function, which efficiently detects anomalies by
NeuEdge: A Neuromorphic Computing Framework for Energy-Efficient Edge AI with Adaptive Spiking Neural Networks
Edge AI applications increasingly require ultra-low-power, low-latency inference. Neuromorphic computing based on event-driven spiking neura
arxiv.org·19d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.