Deep Learning

Mathematics and Theory in Deep Learning with Aleksandr Petiushko
Fireside chat about the importance of Math and Theory for ML/DL roles.
Nov 9, 2022 12:00 AM DLS Podcasts
Aleksandr Petiushko Александр Петюшко
YT Podcast Google Podcasts Apple Podcasts Spotify Spotify for Podcasters Yandex Music In Russian
Mathematics and Theory in Deep Learning with Aleksandr Petiushko
Certified Robustness via Randomized Smoothing over Multiplicative Parameters of Input Transformations
A novel method of certified robustness using Rayleigh dostribution for smoothing when transformations consist not additive but multiplicative group.
Nikita Muravev, Aleksandr Petiushko Александр Петюшко
PDF Cite Video Source Document DOI arXiv
Certified Robustness via Randomized Smoothing over Multiplicative Parameters of Input Transformations
Quadric Hypersurface Intersection for Manifold Learning in Feature Space
A novel approach to use the so-called “Manifold Hypothesis” in order to solve the outlier detection problem by quadrics on top of FaceID embeddings.
Fedor Pavutnitskiy, Sergei O. Ivanov, Evgeniy Abramov, Viacheslav Borovitskiy, Artem Klochkov, Viktor Vyalov, Anatolii Zaikovskii, Aleksandr Petiushko Александр Петюшко
PDF Cite Code Video Source Document arXiv
Quadric Hypersurface Intersection for Manifold Learning in Feature Space
CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networks
A theoretical approach to estimate the certified robustness tested on different image transformations.
Mikhail Pautov, Nurislam Tursynbek, Marina Munkhoeva, Nikita Muravev, Aleksandr Petiushko Александр Петюшко, Ivan Oseledets
PDF Cite Poster Source Document DOI arXiv
CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networks
Geometry-Inspired Top-K Adversarial Perturbations
A simple geometrical approach for crafting top-k adversarial perturbations.
Nurislam Tursynbek, Aleksandr Petiushko Александр Петюшко, Ivan Oseledets
PDF Cite Video Source Document DOI arXiv
Geometry-Inspired Top-K Adversarial Perturbations
Nonparametric Uncertainty Quantification for Single Deterministic Neural Network
Elegant way of measuring both aleatoric and epistemic uncertainties for neural nets.
Nikita Kotelevskii, Alexander Fishkov, Kirill Fedyanin, Aleksandr Petiushko Александр Петюшко, Maxim Panov
PDF Cite arXiv OpenReview Conf WorkshopWeb
Nonparametric Uncertainty Quantification for Single Deterministic Neural Network
Interviews in Deep Learning research with Aleksandr Petiushko
Fireside chat about ML/DL interviews.
Sep 3, 2021 12:00 AM DLS Podcasts
Aleksandr Petiushko Александр Петюшко
YT Podcast Google Podcasts Apple Podcasts Spotify Spotify for Podcasters Yandex Music In Russian
Interviews in Deep Learning research with Aleksandr Petiushko
Manifold Hypothesis in Data Analysis: Double Geometrically-Probabilistic Approach to Manifold Dimension Estimation
Elegant ways to check the so-called “Manifold Hypothesis” for FaceID using geoemtric (Ninkiwsky-based) and probabilistic approaches.
Alexander Ivanov, Gleb Nosovskiy, Alexey Chekunov, Denis Fedoseev, Vladislav Kibkalo, Mikhail Nikulin, Fedor Popelenskiy, Stepan Komkov, Ivan Mazurenko, Aleksandr Petiushko Александр Петюшко
PDF Cite DOI arXiv
Manifold Hypothesis in Data Analysis: Double Geometrically-Probabilistic Approach to Manifold Dimension Estimation
Darker than Black-Box: Face Reconstruction from Similarity Queries
Reconstruction of a face embedding using only similarity score from FaceID system.
Anton Razzhigaev, Klim Kireev, Igor Udovichenko, Aleksandr Petiushko Александр Петюшко
PDF Cite Code DOI arXiv
Darker than Black-Box: Face Reconstruction from Similarity Queries
MDMMT: Multidomain Multimodal Transformer for Video Retrieval
A State-of-the-Art Video Retrieval Method.
Maksim Dzabraev, Maksim Kalashnikov, Stepan Komkov, Aleksandr Petiushko Александр Петюшко
PDF Cite Code Slides Video Source Document DOI arXiv WorkshopWeb
MDMMT: Multidomain Multimodal Transformer for Video Retrieval