Zobrazeno 1 - 10
of 133
pro vyhledávání: '"Smirnov, Petr"'
Autor:
Smith, Ian, Ortmann, Janosch, Abbas-Aghababazadeh, Farnoosh, Smirnov, Petr, Haibe-Kains, Benjamin
Cosine similarity is an established similarity metric for computing associations on vectors, and it is commonly used to identify related samples from biological perturbational data. The distribution of cosine similarity changes with the covariance of
Externí odkaz:
http://arxiv.org/abs/2310.13994
Autor:
Yang, Xuelin, Abraham, Louis, Kim, Sejin, Smirnov, Petr, Ruan, Feng, Haibe-Kains, Benjamin, Tibshirani, Robert
The Cox proportional hazards model is a canonical method in survival analysis for prediction of the life expectancy of a patient given clinical or genetic covariates -- it is a linear model in its original form. In recent years, several methods have
Externí odkaz:
http://arxiv.org/abs/2208.09793
Autor:
Smayev, Mikhail P., Smirnov, Petr A., Budagovsky, Ivan A., Fedyanina, Maria E., Glukhenkaya, Victoria B., Romashkin, Alexey V., Lazarenko, Petr I., Kozyukhin, Sergey A.
Publikováno v:
In Journal of Non-Crystalline Solids 1 June 2024 633
Autor:
Smirnov, Petr, Smith, Ian, Safikhani, Zhaleh, Ba-alawi, Wail, Khodakarami, Farnoosh, Lin, Eva, Yu, Yihong, Martin, Scott, Ortmann, Janosch, Aittokallio, Tero, Hafner, Marc, Haibe-Kains, Benjamin
dentifying associations among biological variables is a major challenge in modern quantitative biological research, particularly given the systemic and statistical noise endemic to biological systems. Drug sensitivity data has proven to be a particul
Externí odkaz:
http://arxiv.org/abs/2104.14036
Autor:
Podmore, Lauren, Poloz, Yekaterina, Iorio, Catherine, Mouaaz, Samar, Nixon, Kevin, Smirnov, Petr, McDonnell, Brianna, Lam, Sonya, Zhang, Bowen, Tharmapalan, Pirashaanthy, Sarkar, Soumili, Vyas, Foram, Ennis, Marguerite, Dowling, Ryan, Stambolic, Vuk
Publikováno v:
In Cell Reports 28 November 2023 42(11)
Deep learning algorithms have increasingly been shown to lack robustness to simple adversarial examples (AdvX). An equally troubling observation is that these adversarial examples transfer between different architectures trained on different datasets
Externí odkaz:
http://arxiv.org/abs/1904.07980
Many deep learning algorithms can be easily fooled with simple adversarial examples. To address the limitations of existing defenses, we devised a probabilistic framework that can generate an exponentially large ensemble of models from a single model
Externí odkaz:
http://arxiv.org/abs/1808.06645
We present two deep generative models based on Variational Autoencoders to improve the accuracy of drug response prediction. Our models, Perturbation Variational Autoencoder and its semi-supervised extension, Drug Response Variational Autoencoder (Dr
Externí odkaz:
http://arxiv.org/abs/1706.08203
Publikováno v:
In Transportation Research Procedia 2021 57:639-645
Autor:
Smirnov, Petr1,2 (AUTHOR), Smith, Ian1,2 (AUTHOR), Safikhani, Zhaleh2 (AUTHOR), Ba-alawi, Wail2 (AUTHOR), Khodakarami, Farnoosh2 (AUTHOR), Lin, Eva3 (AUTHOR), Yu, Yihong3 (AUTHOR), Martin, Scott3 (AUTHOR), Ortmann, Janosch4 (AUTHOR), Aittokallio, Tero5,6,7,8 (AUTHOR), Hafner, Marc9 (AUTHOR), Haibe-Kains, Benjamin1,2,10 (AUTHOR) bhaibeka@uhnresearch.ca
Publikováno v:
BMC Bioinformatics. 5/18/2022, Vol. 23 Issue 1, p1-24. 24p.