“I actually work on this project! Feel free to ask any questions. Also, here’s an arxiv link to one of the papers if anyone is interested: https://arxiv.org/abs/2108.00275”
Demonstration of Decentralized, Physics-Driven Learning
In typical artificial neural networks, neurons adjust according to global calculations of a central processor, but in the brain neurons and synapses self-adjust based on local information. Contrastive learning algorithms have recently been proposed to train physical systems, such as fluidic, mechanical, or electrical networks, to perform machine learning tasks from local evolution rules. However, to date such systems have only been implemented in silico due to the engineering challenge of creating elements that autonomously evolve based on their own response to two sets of global boundary conditions. Here we introduce and implement a physics-driven contrastive learning scheme for a network of variable resistors, using circuitry to locally compare the response of two identical networks subjected to the two different sets of boundary conditions. Using this innovation, our system effectively trains itself, optimizing its resistance values without use of a central processor or external information storage. Once the system is trained for a specified allostery, regression, or classification task, the task is subsequently performed rapidly and automatically by the physical imperative to minimize power dissipation in response to the given voltage inputs. We demonstrate that, unlike typical computers, such learning systems are robust to extreme damage (and thus manufacturing defects) due to their decentralized learning. Our twin-network approach is therefore readily scalable to extremely large or nonlinear networks where its distributed nature will be an enormous advantage; a laboratory network of only 500 edges will already outpace its in silico counterpart.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“You are right of course that it shouldn't, but in practice it always is. The pragmatic reason for that is that if a team spends a month and a few thousand dollars developing and tuning a system, and then they find that the first time they test it on their held-out test set it doesn't work, there is no way that they'll just drop it and accept that all the…”
- Demonstration of Decentralized, Physics-Driven Learning ↗DeadNeurons · 2022-06-02 · 1 分