Oceania
Deep Model Reassembly Xingyi Y ang 1 Daquan Zhou 1,2 Songhua Liu 1 Jingwen Y e
Specifically, we conduct the partitions of all pre-trained networks jointly via a cover set optimization, and derive a number of equivalence set, within each of which the network blocks are treated as functionally equivalent and hence interchangeable.
Supplementary document
This work was partially supported by NIH R01AG027161 and R01EY032284. This research has also received funding from the program "Investissements d'avenir" ANR-10-IAIHU-06. This work was also funded in part by the French government under management of Agence Nationale de la Recherche as part of the "Investissements d'avenir" program, reference ANR-19-P3IA-0001 (PRAIRIE 3IA
LAION-5B: An open large-scale dataset for training next generation image-text models
Studying the training and capabilities of such models requires datasets containing billions of image-text pairs. Until now, no datasets of this size have been made openly available for the broader research community.
Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion
However, their performance usually suffers from the overfitting problem seriously.
On the Equivalence between Neural Network and Support Vector Machine
Recent research has made some progress towards deep learning theory from the perspective of infinite-width NN.