analiza aiqbench
This research demonstrates a breakthrough in energy-efficient AI by converting thermal noise from magnetic tunnel junctions into intrinsic plasticity, enabling human-like working memory within neuromorphic hardware. The approach achieves an 18x reduction in error rates for dynamic vision tasks and cuts memory-energy overhead by over 90,000 times compared to traditional digital systems. By leveraging thermodynamic dissipation as a temporal filter rather than suppressing it, this paradigm offers a viable path toward overcoming the unsustainable energy costs of current large-scale AI models.
Human-like working memory signatures emerge from intrinsically plastic artificial neurons for robust dynamic vision
arXiv:2512.15829v4 Announce Type: replace-cross Abstract: While the unsustainable energy cost of artificial intelligence necessitates physics-driven computing, its performance superiority over full-precision GPUs remains a challenge. We bridge this gap by repurposing the Joule-heating relaxation dynamics of magnetic tunnel junctions, conventionally suppressed as noise, into neuronal intrinsic plasticity, realizing working memory with human-like features. Traditional AI utilizes energy-intensive digital memory that accumulates historical noise in dynamic environments. Conversely, our Intrinsic Plasticity Network (IPNet) leverages thermodynamic dissipation as a temporal filter. We provide direct system-level evidence that this physics-driven memory yields an 18x error reduction compared to spatiotemporal convolutional models in dynamic vision tasks, reducing memory-energy overhead by >90,000x. In autonomous driving, IPNet reduces prediction errors by 12.4% versus recurrent networks. This establishes a neuromorphic paradigm that shatters efficiency limits and surpasses conventional algorithmic performance.
Abstract:While the unsustainable energy cost of artificial intelligence necessitates physics-driven computing, its performance superiority over full-precision GPUs remains a challenge. We bridge this gap by repurposing the Joule-heating relaxation dynamics of magnetic tunnel junctions, conventionally suppressed as noise, into neuronal intrinsic plasticity, realizing working memory with human-like features. Traditional AI utilizes energy-intensive digital memory that accumulates historical noise in dynamic environments. Conversely, our Intrinsic Plasticity Network (IPNet) leverages thermodynamic dissipation as a temporal filter. We provide direct system-level evidence that this physics-driven memory yields an 18x error reduction compared to spatiotemporal convolutional models in dynamic vision tasks, reducing memory-energy overhead by >90,000x. In autonomous driving, IPNet reduces prediction errors by 12.4% versus recurrent networks. This establishes a neuromorphic paradigm that shatters efficiency limits and surpasses conventional algorithmic performance.
Emerging Technologies (cs.ET); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Neural and Evolutionary Computing (cs.NE)
arXiv:2512.15829 [cs.ET]
(or arXiv:2512.15829v4 [cs.ET] for this version)
Text integral sub licența deschisă a publicației · 153 cuvinte
Subiecte conexe
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · 26 aug. 2026
World Models and Yann LeCun’s Bet Against Large Language Models
Quantum Zeitgeist · 17 iul. 2026
Models Can't Remember Their Training. Neither Can You.
LessWrong · 19 iul. 2026
The J-Space Debate, Agent Swarms, and Pacing Frontier AI - Digital Minds Newsletter #4
LessWrong · 18 sept. 2026