Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Rolnick, David S."'
Autor:
Lange, Richard D., Kwok, Devin, Matelsky, Jordan, Wang, Xinyue, Rolnick, David S., Kording, Konrad P.
Deep neural networks implement a sequence of layer-by-layer operations that are each relatively easy to understand, but the resulting overall computation is generally difficult to understand. We consider a simple hypothesis for interpreting the layer
Externí odkaz:
http://arxiv.org/abs/2206.10999
Publikováno v:
TMLR June (2022)
It has been hypothesized that some form of "modular" structure in artificial neural networks should be useful for learning, compositionality, and generalization. However, defining and quantifying modularity remains an open problem. We cast the proble
Externí odkaz:
http://arxiv.org/abs/2203.11815