Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Pradeep Ravikumar"'
Autor:
Chih‐Kuan Yeh, Pradeep Ravikumar
Publikováno v:
Applied AI Letters, Vol 2, Iss 4, Pp n/a-n/a (2021)
Abstract Objective criteria to evaluate the performance of machine learning (ML) model explanations are a critical ingredient in bringing greater rigor to the field of explainable artificial intelligence. In this article, we survey three of our propo
Externí odkaz:
https://doaj.org/article/0c6d23f22d4c4605901f9151d4c259b9
Autor:
Viswanadham Sridhara, Austin G Meyer, Piyush Rai, Jeffrey E Barrick, Pradeep Ravikumar, Daniel Segrè, Claus O Wilke
Publikováno v:
PLoS ONE, Vol 9, Iss 12, p e114608 (2014)
A widely studied problem in systems biology is to predict bacterial phenotype from growth conditions, using mechanistic models such as flux balance analysis (FBA). However, the inverse prediction of growth conditions from phenotype is rarely consider
Externí odkaz:
https://doaj.org/article/2b9f8dd1d3a44e7ca57f85fc6e46abba
Understanding complex machine learning models such as deep neural networks with explanations is crucial in various applications. Many explanations stem from the model perspective, and may not necessarily effectively communicate why the model is makin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0dfc033ebf8ed04b276764b4015f9fce
https://doi.org/10.3233/faia210362
https://doi.org/10.3233/faia210362
Autor:
Pradeep Ravikumar, Chih-Kuan Yeh
Publikováno v:
Applied AI Letters, Vol 2, Iss 4, Pp n/a-n/a (2021)
Objective criteria to evaluate the performance of machine learning (ML) model explanations are a critical ingredient in bringing greater rigor to the field of explainable artificial intelligence. In this article, we survey three of our proposed crite
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9185a1b86935da85955175e21ba20bd
https://doi.org/10.1002/ail2.57
https://doi.org/10.1002/ail2.57
Publikováno v:
ACL/IJCNLP (2)
Compositional generalization is the ability to generalize systematically to a new data distribution by combining known components. Although humans seem to have a great ability to generalize compositionally, state-of-the-art neural models struggle to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d47cc5f6144e5be62dc3618df1161627
https://doi.org/10.18653/v1/2021.acl-short.81
https://doi.org/10.18653/v1/2021.acl-short.81
Publikováno v:
Ann. Statist. 48, no. 4 (2020), 2277-2302
Motivated by problems in data clustering, we establish general conditions under which families of nonparametric mixture models are identifiable, by introducing a novel framework involving clustering overfitted \emph{parametric} (i.e. misspecified) mi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::356984ad233bded9ddd7d9a22059b88f
https://projecteuclid.org/euclid.aos/1597370673
https://projecteuclid.org/euclid.aos/1597370673
Autor:
Ian E H, Yen, Wei-Cheng, Lee, Sung-En, Chang, Arun S, Suggala, Shou-De, Lin, Pradeep, Ravikumar
Publikováno v:
Proceedings of machine learning research. 70
The latent feature model (LFM), proposed in (Griffiths & Ghahramani, 2005), but possibly with earlier origins, is a generalization of a mixture model, where each instance is generated not from a single latent class but from a combination of latent fe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::96ebe112fc231bcf175918fa509ee48a
https://pubmed.ncbi.nlm.nih.gov/31225526
https://pubmed.ncbi.nlm.nih.gov/31225526
Autor:
Fangli Xu, Pin-Yu Chen, Avinash Balakrishnan, Lingfei Wu, Michael Witbrock, Kun Xu, Pradeep Ravikumar, Ian En-Hsu Yen
Publikováno v:
EMNLP
While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings. Recent work has demonstrated that a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fed19f7f63f29735f338d42b1c849d46
https://doi.org/10.18653/v1/d18-1482
https://doi.org/10.18653/v1/d18-1482
We provide a new computationally-efficient class of estimators for risk minimization. We show that these estimators are robust for general statistical models: in the classical Huber epsilon-contamination model and in heavy-tailed settings. Our workho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08f35634c4e194f750424da5749f4b1d
Autor:
Ritesh Noothigattu, Snehalkumar Gaikwad, Edmond Awad, Sohan Dsouza, Iyad Rahwan, Pradeep Ravikumar, Ariel Procaccia
Publikováno v:
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)
arXiv
arXiv
We present a general approach to automating ethical decisions, drawing on machine learning and computational social choice. In a nutshell, we propose to learn a model of societal preferences, and, when faced with a specific ethical dilemma at runtime
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef703d5ac90a3863d60d2087b02b8830
https://hdl.handle.net/21.11116/0000-0003-3F53-A21.11116/0000-0003-1E34-2
https://hdl.handle.net/21.11116/0000-0003-3F53-A21.11116/0000-0003-1E34-2