按年被提到
20162017 · 1 次2026
机器学习与深度学习›科学机器学习·arXiv:1612.00222 · cs.AI

Interaction Networks for Learning about Objects, Relations and Physics

Peter W. Battaglia, Razvan Pascanu, Matthew Lai, Danilo Rezende, Koray Kavukcuoglu · 2016
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2017-02-05 · 最近 2023-09-19
2不同的人
2活跃月份
2讨论串
925被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Reasoning about objects, relations, and physics is central to human intelligence, and a key goal of artificial intelligence. Here we introduce the interaction network, a model which can reason about how objects in complex systems interact, supporting dynamical predictions, as well as inferences about the abstract properties of the system. Our model takes graphs as input, performs object- and relation-centric reasoning in a way that is analogous to a simulation, and is implemented using deep neural networks. We evaluate its ability to reason about several challenging physical domains: n-body problems, rigid-body collision, and non-rigid dynamics. Our results show it can be trained to accurately simulate the physical trajectories of dozens of objects over thousands of time steps, estimate abstract quantities such as energy, and generalize automatically to systems with different numbers and configurations of objects and relations. Our interaction network implementation is the first general-purpose, learnable physics engine, and a powerful general framework for reasoning about object and relations in a wide variety of complex real-world domains.

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
评论Seanny123 · 2017-02

“I'm honestly just super-pumped about any artificial intelligence system that's starting to get an intuition of physics. Google's Deep Mind put out some kind of cool stuff recentely [1], but I'm mostly just excited for anything that Ilker Yildirim [2] is doing with Joshua Tanenbaum, because it seems to triangulate more with how humans think about physics.…”

Ask HN: What is the most exciting development in your field right now?原评论 ↗
评论stefanpie · 2023-09

“I've work with GNNs. I have not explicitly looked into this, but in general, the dynamics of GNNs are really interesting and there are many different lenses in which one can study the behavior of GNNs and find interesting takeaways. - Explicit Message Passing: https://arxiv.org/abs/2202.11097 - Algorithmic Reasoning: https://arxiv.org/abs/2203.15544 - …”

Graph Neural Networks Use Graphs When They Shouldn't原评论 ↗