all AI news
Deep Neural Networks Tend To Extrapolate Predictably
March 19, 2024, 4:44 a.m. | Katie Kang, Amrith Setlur, Claire Tomlin, Sergey Levine
cs.LG updates on arXiv.org arxiv.org
Abstract: Conventional wisdom suggests that neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. Our work reassesses this assumption for neural networks with high-dimensional inputs. Rather than extrapolating in arbitrary ways, we observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. Moreover, we find that this value often closely approximates the optimal constant solution (OCS), i.e., the prediction that minimizes the average …
abstract arxiv cs.lg distribution inputs network networks neural network neural networks observe predictions type value work
More from arxiv.org / cs.LG updates on arXiv.org
The Perception-Robustness Tradeoff in Deterministic Image Restoration
2 days, 4 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne