all AI news
Deeper Understanding of Black-box Predictions via Generalized Influence Functions
May 7, 2024, 4:45 a.m. | Hyeonsu Lyu, Jonggyu Jang, Sehyun Ryu, Hyun Jong Yang
cs.LG updates on arXiv.org arxiv.org
Abstract: Influence functions (IFs) elucidate how training data changes model behavior. However, the increasing size and non-convexity in large-scale models make IFs inaccurate. We suspect that the fragility comes from the first-order approximation which may cause nuisance changes in parameters irrelevant to the examined data. However, simply computing influence from the chosen parameters can be misleading, as it fails to nullify the hidden effects of unselected parameters on the analyzed data. Thus, our approach introduces generalized …
arxiv box cs.ai cs.lg functions generalized influence predictions type understanding via
More from arxiv.org / cs.LG updates on arXiv.org
Testing the Segment Anything Model on radiology data
2 days, 6 hours ago |
arxiv.org
Calorimeter shower superresolution
2 days, 6 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US