Zobrazeno 1 - 10
of 398
pro vyhledávání: '"Byrnes, John"'
Autor:
Sikka, Karan, Huang, Jihua, Silberfarb, Andrew, Nayak, Prateeth, Rohrer, Luke, Sahu, Pritish, Byrnes, John, Divakaran, Ajay, Rohwer, Richard
We improve zero-shot learning (ZSL) by incorporating common-sense knowledge in DNNs. We propose Common-Sense based Neuro-Symbolic Loss (CSNL) that formulates prior knowledge as novel neuro-symbolic loss functions that regularize visual-semantic embed
Externí odkaz:
http://arxiv.org/abs/2011.10889
Neural methods of molecule property prediction require efficient encoding of structure and property relationship to be accurate. Recent work using graph algorithms shows limited generalization in the latent molecule encoding space. We build a Transfo
Externí odkaz:
http://arxiv.org/abs/2011.03518
In this work, we present a framework for incorporating descriptive logical rules in state-of-the-art neural networks, enabling them to learn how to handle unseen labels without the introduction of any new training data. The rules are integrated into
Externí odkaz:
http://arxiv.org/abs/2009.13275
Autor:
Sikka, Karan, Silberfarb, Andrew, Byrnes, John, Sur, Indranil, Chow, Ed, Divakaran, Ajay, Rohwer, Richard
We introduce Deep Adaptive Semantic Logic (DASL), a novel framework for automating the generation of deep neural networks that incorporates user-provided formal knowledge to improve learning from data. We provide formal semantics that demonstrate tha
Externí odkaz:
http://arxiv.org/abs/2003.07344
Publikováno v:
In iScience 15 July 2022 25(7)
Thesis (M.S.)--Massachusetts Institute of Technology, Sloan School of Management, 1990.
Includes bibliographical references (leaf 88).
by John M. Byrnes.
M.S.
Includes bibliographical references (leaf 88).
by John M. Byrnes.
M.S.
Externí odkaz:
http://hdl.handle.net/1721.1/14265