all AI news
DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation [Technical Report]. (arXiv:2104.02234v7 [cs.DB] CROSS LISTED)
cs.LG updates on arXiv.org arxiv.org
We design, implement, and evaluate DeepEverest, a system for the efficient
execution of interpretation by example queries over the activation values of a
deep neural network. DeepEverest consists of an efficient indexing technique
and a query execution algorithm with various optimizations. We prove that the
proposed query execution algorithm is instance optimal. Experiments with our
prototype show that DeepEverest, using less than 20% of the storage of full
materialization, significantly accelerates individual queries by up to 63x and
consistently outperforms …
arxiv deep neural network network neural network report technical top