all AI news
Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality. (arXiv:2207.02119v1 [cs.CV])
July 6, 2022, 1:12 a.m. | Yue Song, Nicu Sebe, Wei Wang
cs.CV updates on arXiv.org arxiv.org
Inserting an SVD meta-layer into neural networks is prone to make the
covariance ill-conditioned, which could harm the model in the training
stability and generalization abilities. In this paper, we systematically study
how to improve the covariance conditioning by enforcing orthogonality to the
Pre-SVD layer. Existing orthogonal treatments on the weights are first
investigated. However, these techniques can improve the conditioning but would
hurt the performance. To avoid such a side effect, we propose the Nearest
Orthogonal Gradient (NOG) and …
More from arxiv.org / cs.CV updates on 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