Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Elango, Mahalaxmi"'
Autor:
Elango, Mahalaxmi
Observations of various deep neural network architectures indicate that deep networks may be spontaneously learning representations of concepts with semantic meaning, and encoding a relational structure or rule between these concepts. We refer to the
Externí odkaz:
https://hdl.handle.net/1721.1/139151
Autor:
Santurkar, Shibani, Tsipras, Dimitris, Elango, Mahalaxmi, Bau, David, Torralba, Antonio, Madry, Aleksander
We present a methodology for modifying the behavior of a classifier by directly rewriting its prediction rules. Our approach requires virtually no additional data collection and can be applied to a variety of settings, including adapting a model to n
Externí odkaz:
http://arxiv.org/abs/2112.01008