Sub-picojoule-per-bit volitional neuromorphic devices for precise targeting and tracking
Yixuan Huang, Qihao Sun, Fuxing Dai, Fang Wang et autres
The technological revolution driven by artificial intelligence has significantly improved the hardware performance, but energy consumption remains a critical bottleneck. The state-of-the-art retinomorphic devices, as core components of artificial intelligence hardware, excel in feature extraction but are constrained by passive attention mechanisms …
cn, gb (code pays fourni par la source)
6 citations
Nature Communications