Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Somnath Basu Roy Chowdhury"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 10, Pp 1159-1174 (2022)
AbstractText representations learned by machine learning models often encode undesirable demographic information of the user. Predictive models based on these representations can rely on such information, resulting in biased decisions. We present a n
Externí odkaz:
https://doaj.org/article/7657dd6258354bb58ee762fbd38e456e
Autor:
Somnath Basu Roy Chowdhury, Sayan Ghosh, Yiyuan Li, Junier Oliva, Shashank Srivastava, Snigdha Chaturvedi
Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task. We aim to scrub such undesirable attributes and learn fair re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::90b940f596e8df4f5fbd45d4caa6c779
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 32
Global average pooling (GAP) has been used previously to generate class activation maps. The motivation behind AdGAP comes from the fact that the convolutional filters possess position information of the essential features and hence, combination of t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dbde05308031758f09b44e40cb22343b
https://doi.org/10.1609/aaai.v32i1.12154
https://doi.org/10.1609/aaai.v32i1.12154
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 32
Autoencoders (AE) are essential in learning representation of large data (like images) for dimensionality reduction. Images are converted to sparse domain using transforms like Fast Fourier Transform (FFT) or Discrete Cosine Transform (DCT) where inf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c54a242be3adeda6d1a1cd1939c051f2
https://doi.org/10.1609/aaai.v32i1.12155
https://doi.org/10.1609/aaai.v32i1.12155
Publikováno v:
DeepLo@EMNLP-IJCNLP
Supervised learning models are typically trained on a single dataset and the performance of these models rely heavily on the size of the dataset, i.e., amount of data available with the ground truth. Learning algorithms try to generalize solely based
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b49c086bb031c53f4ba39f7c97955278
http://arxiv.org/abs/1802.05934
http://arxiv.org/abs/1802.05934
Publikováno v:
NAACL-HLT
Machine Learning has been the quintessential solution for many AI problems, but learning is still heavily dependent on the specific training data. Some learning models can be incorporated with a prior knowledge in the Bayesian set up, but these learn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aad57ae11e58a0817d0ca804fd7456cf
https://doi.org/10.18653/v1/n18-1029
https://doi.org/10.18653/v1/n18-1029