all AI news
OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses
April 16, 2024, 4:44 a.m. | Robik Shrestha, Kushal Kafle, Christopher Kanan
cs.LG updates on arXiv.org arxiv.org
Abstract: Dataset bias and spurious correlations can significantly impair generalization in deep neural networks. Many prior efforts have addressed this problem using either alternative loss functions or sampling strategies that focus on rare patterns. We propose a new direction: modifying the network architecture to impose inductive biases that make the network robust to dataset bias. Specifically, we propose OccamNets, which are biased to favor simpler solutions by design. OccamNets have two inductive biases. First, they are …
abstract architecture arxiv bias biases correlations cs.lg dataset focus functions inductive loss network network architecture networks neural networks patterns prior sampling strategies type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
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
Lead Data Scientist, Commercial Analytics
@ Checkout.com | London, United Kingdom
Data Engineer I
@ Love's Travel Stops | Oklahoma City, OK, US, 73120