Search Results for author: Evgeny Burnaev

Found 126 papers, 49 papers with code

Bayesian Sparsification of Deep C-valued Networks

1 code implementation ICML 2020 Ivan Nazarov, Evgeny Burnaev

With continual miniaturization ever more applications of deep learning can be found in embedded systems, where it is common to encounter data with natural representation in the complex domain.

Music Transcription

Multi-NeuS: 3D Head Portraits from Single Image with Neural Implicit Functions

no code implementations7 Sep 2022 Egor Burkov, Ruslan Rakhimov, Aleksandr Safin, Evgeny Burnaev, Victor Lempitsky

Namely, we extend NeuS, a state-of-the-art neural implicit function formulation, to represent multiple objects of a class (human heads in our case) simultaneously.

3D Reconstruction

Transfer learning for ensembles: reducing computation time and keeping the diversity

no code implementations27 Jun 2022 Ilya Shashkov, Nikita Balabin, Evgeny Burnaev, Alexey Zaytsev

Our approach for the transfer learning of ensembles consists of two steps: (a) shifting weights of encoders of all models in the ensemble by a single shift vector and (b) doing a tiny fine-tuning for each individual model afterwards.

Transfer Learning

Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?

3 code implementations15 Jun 2022 Alexander Korotin, Alexander Kolesov, Evgeny Burnaev

Despite the success of WGANs, it is still unclear how well the underlying OT dual solvers approximate the OT cost (Wasserstein-1 distance, $\mathbb{W}_{1}$) and the OT gradient needed to update the generator.

Neural Optimal Transport with General Cost Functionals

no code implementations30 May 2022 Arip Asadulaev, Alexander Korotin, Vage Egiazarian, Evgeny Burnaev

We present a novel neural-networks-based algorithm to compute optimal transport (OT) plans and maps for general cost functionals.

Kernel Neural Optimal Transport

no code implementations30 May 2022 Alexander Korotin, Daniil Selikhanovych, Evgeny Burnaev

We study the Neural Optimal Transport (NOT) algorithm which uses the general optimal transport formulation and learns stochastic transport plans.

Image-to-Image Translation Translation

NPBG++: Accelerating Neural Point-Based Graphics

1 code implementation CVPR 2022 Ruslan Rakhimov, Andrei-Timotei Ardelean, Victor Lempitsky, Evgeny Burnaev

We present a new system (NPBG++) for the novel view synthesis (NVS) task that achieves high rendering realism with low scene fitting time.

Novel View Synthesis

Neural Optimal Transport

no code implementations28 Jan 2022 Alexander Korotin, Daniil Selikhanovych, Evgeny Burnaev

We present a novel neural-networks-based algorithm to compute optimal transport maps and plans for strong and weak transport costs.


Wasserstein Iterative Networks for Barycenter Estimation

no code implementations28 Jan 2022 Alexander Korotin, Vage Egiazarian, Lingxiao Li, Evgeny Burnaev

Wasserstein barycenters have become popular due to their ability to represent the average of probability measures in a geometrically meaningful way.

Development of Deep Transformer-Based Models for Long-Term Prediction of Transient Production of Oil Wells

no code implementations12 Oct 2021 Ildar Abdrakhmanov, Evgenii Kanin, Sergei Boronin, Evgeny Burnaev, Andrei Osiptsov

We apply the transfer learning procedure to the transformer-based surrogate model, which includes the initial training on the dataset from a certain well and additional tuning of the model's weights on the dataset from a target well.

Time Series Transfer Learning

Generative Modeling with Optimal Transport Maps

1 code implementation ICLR 2022 Litu Rout, Alexander Korotin, Evgeny Burnaev

In particular, we consider denoising, colorization, and inpainting, where the optimality of the restoration map is a desired attribute, since the output (restored) image is expected to be close to the input (degraded) one.

Colorization Denoising +2

Artificial Text Detection via Examining the Topology of Attention Maps

1 code implementation EMNLP 2021 Laida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev

The impressive capabilities of recent generative models to create texts that are challenging to distinguish from the human-written ones can be misused for generating fake news, product reviews, and even abusive content.

Topological Data Analysis

Data-driven model for hydraulic fracturing design optimization. Part II: Inverse problem

no code implementations2 Aug 2021 Viktor Duplyakov, Anton Morozov, Dmitriy Popkov, Egor Shel, Albert Vainshtein, Evgeny Burnaev, Andrei Osiptsov, Grigory Paderin

We developed a set of methods including those based on the use of Euclidean distance and clustering techniques to perform similar (offset) wells search, which is useful for a field engineer to analyze earlier fracturing treatments on similar wells.

A Differentiable Language Model Adversarial Attack on Text Classifiers

no code implementations23 Jul 2021 Ivan Fursov, Alexey Zaytsev, Pavel Burnyshev, Ekaterina Dmitrieva, Nikita Klyuchnikov, Andrey Kravchenko, Ekaterina Artemova, Evgeny Burnaev

Moreover, due to the usage of the fine-tuned language model, the generated adversarial examples are hard to detect, thus current models are not robust.

Adversarial Attack Language Modelling

3D Parametric Wireframe Extraction Based on Distance Fields

no code implementations13 Jul 2021 Albert Matveev, Alexey Artemov, Denis Zorin, Evgeny Burnaev

We present a pipeline for parametric wireframe extraction from densely sampled point clouds.

Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark

3 code implementations NeurIPS 2021 Alexander Korotin, Lingxiao Li, Aude Genevay, Justin Solomon, Alexander Filippov, Evgeny Burnaev

Despite the recent popularity of neural network-based solvers for optimal transport (OT), there is no standard quantitative way to evaluate their performance.

Image Generation

Large-Scale Wasserstein Gradient Flows

3 code implementations NeurIPS 2021 Petr Mokrov, Alexander Korotin, Lingxiao Li, Aude Genevay, Justin Solomon, Evgeny Burnaev

Specifically, Fokker-Planck equations, which model the diffusion of probability measures, can be understood as gradient descent over entropy functionals in Wasserstein space.

Unpaired Depth Super-Resolution in the Wild

no code implementations25 May 2021 Aleksandr Safin, Maxim Kan, Nikita Drobyshev, Oleg Voynov, Alexey Artemov, Alexander Filippov, Denis Zorin, Evgeny Burnaev

We propose an unpaired learning method for depth super-resolution, which is based on a learnable degradation model, enhancement component and surface normal estimates as features to produce more accurate depth maps.

Depth Map Super-Resolution Image-to-Image Translation +1

Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization

2 code implementations ICLR 2021 Alexander Korotin, Lingxiao Li, Justin Solomon, Evgeny Burnaev

Wasserstein barycenters provide a geometric notion of the weighted average of probability measures based on optimal transport.

Denoising Score Matching with Random Fourier Features

no code implementations13 Jan 2021 Tsimboy Olga, Yermek Kapushev, Evgeny Burnaev, Ivan Oseledets

In this work we derive analytical expression for the Denoising Score matching using the Kernel Exponential Family as a model distribution.

Denoising Density Estimation

Topological obstructions in neural networks learning

no code implementations31 Dec 2020 Serguei Barannikov, Daria Voronkova, Ilya Trofimov, Alexander Korotin, Grigorii Sotnikov, Evgeny Burnaev

We define the neural network Topological Obstructions score, "TO-score", with the help of robust topological invariants, barcodes of the loss function, that quantify the "badness" of local minima for gradient-based optimization.

Topological Data Analysis

Relightable 3D Head Portraits from a Smartphone Video

no code implementations17 Dec 2020 Artem Sevastopolsky, Savva Ignatiev, Gonzalo Ferrer, Evgeny Burnaev, Victor Lempitsky

The model is fitted to the sequence of frames with human face-specific priors that enforce the plausibility of albedo-lighting decomposition and operates at the interactive frame rate.


Towards Part-Based Understanding of RGB-D Scans

1 code implementation CVPR 2021 Alexey Bokhovkin, Vladislav Ishimtsev, Emil Bogomolov, Denis Zorin, Alexey Artemov, Evgeny Burnaev, Angela Dai

Recent advances in 3D semantic scene understanding have shown impressive progress in 3D instance segmentation, enabling object-level reasoning about 3D scenes; however, a finer-grained understanding is required to enable interactions with objects and their functional understanding.

3D Instance Segmentation Scene Understanding +1

DEF: Deep Estimation of Sharp Geometric Features in 3D Shapes

1 code implementation30 Nov 2020 Albert Matveev, Ruslan Rakhimov, Alexey Artemov, Gleb Bobrovskikh, Vage Egiazarian, Emil Bogomolov, Daniele Panozzo, Denis Zorin, Evgeny Burnaev

We propose Deep Estimators of Features (DEFs), a learning-based framework for predicting sharp geometric features in sampled 3D shapes.

How Good MVSNets Are at Depth Fusion

no code implementations30 Nov 2020 Oleg Voynov, Aleksandr Safin, Savva Ignatyev, Evgeny Burnaev

We study the effects of the additional input to deep multi-view stereo methods in the form of low-quality sensor depth.

Detecting Video Game Player Burnout with the Use of Sensor Data and Machine Learning

no code implementations29 Nov 2020 Anton Smerdov, Andrey Somov, Evgeny Burnaev, Bo Zhou, Paul Lukowicz

In this article, we propose the methods based on the sensor data analysis for predicting whether a player will win the future encounter.

BIG-bench Machine Learning Interpretable Machine Learning +10

Convolutional neural networks for automatic detection of Focal Cortical Dysplasia

1 code implementation20 Oct 2020 Ruslan Aliev, Ekaterina Kondrateva, Maxim Sharaev, Oleg Bronov, Alexey Marinets, Sergey Subbotin, Alexander Bernstein, Evgeny Burnaev

Focal cortical dysplasia (FCD) is one of the most common epileptogenic lesions associated with cortical development malformations.

Fader Networks for domain adaptation on fMRI: ABIDE-II study

1 code implementation14 Oct 2020 Marina Pominova, Ekaterina Kondrateva, Maxim Sharaev, Alexander Bernstein, Evgeny Burnaev

ABIDE is the largest open-source autism spectrum disorder database with both fMRI data and full phenotype description.

Domain Adaptation

Graph Neural Networks for Model Recommendation using Time Series Data

no code implementations8 Sep 2020 Aleksandr Pletnev, Rodrigo Rivera-Castro, Evgeny Burnaev

The results show the relevancy and suitability of GNN as methods for model recommendations in time series forecasting.


Addressing Cold Start in Recommender Systems with Hierarchical Graph Neural Networks

no code implementations7 Sep 2020 Ivan Maksimov, Rodrigo Rivera-Castro, Evgeny Burnaev

Recommender systems have become an essential instrument in a wide range of industries to personalize the user experience.

Recommendation Systems

CAD-Deform: Deformable Fitting of CAD Models to 3D Scans

1 code implementation ECCV 2020 Vladislav Ishimtsev, Alexey Bokhovkin, Alexey Artemov, Savva Ignatyev, Matthias Niessner, Denis Zorin, Evgeny Burnaev

Shape retrieval and alignment are a promising avenue towards turning 3D scans into lightweight CAD representations that can be used for content creation such as mobile or AR/VR gaming scenarios.

Geometric Attention for Prediction of Differential Properties in 3D Point Clouds

no code implementations6 Jul 2020 Albert Matveev, Alexey Artemov, Denis Zorin, Evgeny Burnaev

Estimation of differential geometric quantities in discrete 3D data representations is one of the crucial steps in the geometry processing pipeline.

Surface Reconstruction

Making DensePose fast and light

1 code implementation26 Jun 2020 Ruslan Rakhimov, Emil Bogomolov, Alexandr Notchenko, Fung Mao, Alexey Artemov, Denis Zorin, Evgeny Burnaev

DensePose estimation task is a significant step forward for enhancing user experience computer vision applications ranging from augmented reality to cloth fitting.

3D Human Pose Estimation Quantization

Latent Video Transformer

1 code implementation18 Jun 2020 Ruslan Rakhimov, Denis Volkhonskiy, Alexey Artemov, Denis Zorin, Evgeny Burnaev

After the transformation of frames into the latent space, our model predicts latent representation for the next frames in an autoregressive manner.

Video Generation Video Prediction

Multi-fidelity Neural Architecture Search with Knowledge Distillation

1 code implementation15 Jun 2020 Ilya Trofimov, Nikita Klyuchnikov, Mikhail Salnikov, Alexander Filippov, Evgeny Burnaev

The method relies on a new approach to low-fidelity evaluations of neural architectures by training for a few epochs using a knowledge distillation.

Knowledge Distillation Neural Architecture Search

NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processing

1 code implementation12 Jun 2020 Nikita Klyuchnikov, Ilya Trofimov, Ekaterina Artemova, Mikhail Salnikov, Maxim Fedorov, Evgeny Burnaev

In this work, we step outside the computer vision domain by leveraging the language modeling task, which is the core of natural language processing (NLP).

Language Modelling Neural Architecture Search

Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems

1 code implementation MIDL 2019 Anna Kuzina, Evgenii Egorov, Evgeny Burnaev

Automatic segmentation methods based on deep learning have recently demonstrated state-of-the-art performance, outperforming the ordinary methods.

Brain Tumor Segmentation Transfer Learning +1

Recurrent Convolutional Neural Networks help to predict location of Earthquakes

1 code implementation20 Apr 2020 Roman Kail, Alexey Zaytsev, Evgeny Burnaev

For historical data on Japan earthquakes our model predicts occurrence of an earthquake in $10$ to $60$ days from a given moment with magnitude $M_c > 5$ with quality metrics ROC AUC $0. 975$ and PR AUC $0. 0890$, making $1. 18 \cdot 10^3$ correct predictions, while missing $2. 09 \cdot 10^3$ earthquakes and making $192 \cdot 10^3$ false alarms.

Bayesian Sparsification Methods for Deep Complex-valued Networks

1 code implementation25 Mar 2020 Ivan Nazarov, Evgeny Burnaev

With continual miniaturization ever more applications of deep learning can be found in embedded systems, where it is common to encounter data with natural complex domain representation.

Music Transcription

Data-driven models and computational tools for neurolinguistics: a language technology perspective

1 code implementation23 Mar 2020 Ekaterina Artemova, Amir Bakarov, Aleksey Artemov, Evgeny Burnaev, Maxim Sharaev

In this paper, our focus is the connection and influence of language technologies on the research in neurolinguistics.

Word Embeddings

Software System for Road Condition Forecast Correction

no code implementations22 Mar 2020 Dmitrii Smolyakov, Evgeny Burnaev

In this paper, we present a monitoring system that allows increasing road safety by predicting ice formation.

BIG-bench Machine Learning

Deep Vectorization of Technical Drawings

1 code implementation ECCV 2020 Vage Egiazarian, Oleg Voynov, Alexey Artemov, Denis Volkhonskiy, Aleksandr Safin, Maria Taktasheva, Denis Zorin, Evgeny Burnaev

We present a new method for vectorization of technical line drawings, such as floor plans, architectural drawings, and 2D CAD images.

Gradient-based adversarial attacks on categorical sequence models via traversing an embedded world

no code implementations9 Mar 2020 Ivan Fursov, Alexey Zaytsev, Nikita Kluchnikov, Andrey Kravchenko, Evgeny Burnaev

The first approach adopts a Monte-Carlo method and allows usage in any scenario, the second approach uses a continuous relaxation of models and target metrics, and thus allows usage of state-of-the-art methods for adversarial attacks with little additional effort.

Adversarial Attack

Reinforcement Learning for Combinatorial Optimization: A Survey

no code implementations7 Mar 2020 Nina Mazyavkina, Sergey Sviridov, Sergei Ivanov, Evgeny Burnaev

Many traditional algorithms for solving combinatorial optimization problems involve using hand-crafted heuristics that sequentially construct a solution.

Combinatorial Optimization Decision Making +1

Integral Mixability: a Tool for Efficient Online Aggregation of Functional and Probabilistic Forecasts

no code implementations15 Dec 2019 Alexander Korotin, Vladimir V'yugin, Evgeny Burnaev

In this paper we extend the setting of the online prediction with expert advice to function-valued forecasts.

Latent-Space Laplacian Pyramids for Adversarial Representation Learning with 3D Point Clouds

1 code implementation13 Dec 2019 Vage Egiazarian, Savva Ignatyev, Alexey Artemov, Oleg Voynov, Andrey Kravchenko, Youyi Zheng, Luiz Velho, Evgeny Burnaev

Constructing high-quality generative models for 3D shapes is a fundamental task in computer vision with diverse applications in geometry processing, engineering, and design.

Generating 3D Point Clouds Representation Learning

Tensor Completion via Gaussian Process Based Initialization

no code implementations11 Dec 2019 Yermek Kapushev, Ivan Oseledets, Evgeny Burnaev

In this paper, we consider the tensor completion problem representing the solution in the tensor train (TT) format.

Barcodes as summary of objective function's topology

no code implementations29 Nov 2019 Serguei Barannikov, Alexander Korotin, Dmitry Oganesyan, Daniil Emtsev, Evgeny Burnaev

We apply the canonical forms (barcodes) of gradient Morse complexes to explore topology of loss surfaces.

Weakly Supervised Fine Tuning Approach for Brain Tumor Segmentation Problem

1 code implementation5 Nov 2019 Sergey Pavlov, Alexey Artemov, Maksim Sharaev, Alexander Bernstein, Evgeny Burnaev

Segmentation of tumors in brain MRI images is a challenging task, where most recent methods demand large volumes of data with pixel-level annotations, which are generally costly to obtain.

Brain Tumor Segmentation Tumor Segmentation

Understanding Isomorphism Bias in Graph Data Sets

1 code implementation26 Oct 2019 Sergei Ivanov, Sergei Sviridov, Evgeny Burnaev

In recent years there has been a rapid increase in classification methods on graph structured data.

General Classification Graph Classification

Wasserstein-2 Generative Networks

3 code implementations ICLR 2021 Alexander Korotin, Vage Egiazarian, Arip Asadulaev, Alexander Safin, Evgeny Burnaev

We propose a novel end-to-end non-minimax algorithm for training optimal transport mappings for the quadratic cost (Wasserstein-2 distance).

Domain Adaptation Style Transfer

Barcodes as summary of objective functions' topology

no code implementations25 Sep 2019 Serguei Barannikov, Alexander Korotin, Dmitry Oganesyan, Daniil Emtsev, Evgeny Burnaev

We apply canonical forms of gradient complexes (barcodes) to explore neural networks loss surfaces.

eSports Pro-Players Behavior During the Game Events: Statistical Analysis of Data Obtained Using the Smart Chair

1 code implementation18 Aug 2019 Anton Smerdov, Evgeny Burnaev, Andrey Somov

Today's competition between the professional eSports teams is so strong that in-depth analysis of players' performance literally crucial for creating a powerful team.

Feature Engineering Feature Importance +6

Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems

no code implementations15 Aug 2019 Anna Kuzina, Evgenii Egorov, Evgeny Burnaev

Automatic segmentation methods based on deep learning have recently demonstrated state-of-the-art performance, outperforming the ordinary methods.

Brain Tumor Segmentation Transfer Learning +1

Learning to Approximate Directional Fields Defined over 2D Planes

no code implementations1 Jul 2019 Maria Taktasheva, Albert Matveev, Alexey Artemov, Evgeny Burnaev

Reconstruction of directional fields is a need in many geometry processing tasks, such as image tracing, extraction of 3D geometric features, and finding principal surface directions.

Rare Failure Prediction via Event Matching for Aerospace Applications

no code implementations28 May 2019 Evgeny Burnaev

In this paper, we consider a problem of failure prediction in the context of predictive maintenance applications.

Ensemble of 3D CNN regressors with data fusion for fluid intelligence prediction

no code implementations25 May 2019 Marina Pominova, Anna Kuzina, Ekaterina Kondrateva, Svetlana Sushchinskaya, Maxim Sharaev, Evgeny Burnaev, and Vyacheslav Yarkin

In this work, we aim at predicting children's fluid intelligence scores based on structural T1-weighted MR images from the largest long-term study of brain development and child health.

A Predictive Model for Steady-State Multiphase Pipe Flow: Machine Learning on Lab Data

no code implementations23 May 2019 Evgenii Kanin, Andrei Osiptsov, Albert Vainshtein, Evgeny Burnaev

In order to extend the applicability and the accuracy of the existing accessible methods, a method of pressure drop calculation in the pipeline is proposed.

BIG-bench Machine Learning

Boundary Loss for Remote Sensing Imagery Semantic Segmentation

3 code implementations20 May 2019 Alexey Bokhovkin, Evgeny Burnaev

Convolutional neural networks are powerful visual models that yield hierarchies of features and practitioners widely use them to process remote sensing data.

Boundary Detection Image Segmentation +1

Artificial Neural Network Surrogate Modeling of Oil Reservoir: a Case Study

no code implementations20 May 2019 Oleg Sudakov, Dmitri Koroteev, Boris Belozerov, Evgeny Burnaev

We develop a data-driven model, introducing recent advances in machine learning to reservoir simulation.

Procedural Synthesis of Remote Sensing Images for Robust Change Detection with Neural Networks

1 code implementation20 May 2019 Maria Kolos, Anton Marin, Alexey Artemov, Evgeny Burnaev

Data-driven methods such as convolutional neural networks (CNNs) are known to deliver state-of-the-art performance on image recognition tasks when the training data are abundant.

Change Detection

MaxEntropy Pursuit Variational Inference

no code implementations20 May 2019 Evgenii Egorov, Kirill Neklydov, Ruslan Kostoev, Evgeny Burnaev

One of the core problems in variational inference is a choice of approximate posterior distribution.

Continual Learning Variational Inference

Monocular 3D Object Detection via Geometric Reasoning on Keypoints

no code implementations14 May 2019 Ivan Barabanau, Alexey Artemov, Evgeny Burnaev, Vyacheslav Murashkin

Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D detections.

Keypoint Detection Monocular 3D Object Detection +1

User-Controllable Multi-Texture Synthesis with Generative Adversarial Networks

no code implementations9 Apr 2019 Aibek Alanov, Max Kochurov, Denis Volkhonskiy, Daniil Yashkov, Evgeny Burnaev, Dmitry Vetrov

We propose a novel multi-texture synthesis model based on generative adversarial networks (GANs) with a user-controllable mechanism.

Texture Synthesis

Adaptive Hedging under Delayed Feedback

no code implementations27 Feb 2019 Alexander Korotin, Vladimir V'yugin, Evgeny Burnaev

The article is devoted to investigating the application of hedging strategies to online expert weight allocation under delayed feedback.

Gradient Boosting to Boost the Efficiency of Hydraulic Fracturing

no code implementations5 Feb 2019 Ivan Makhotin, Dmitry Koroteev, Evgeny Burnaev

We discuss the potential for further development of ML techniques for predicting changes in oil rate after HF.

BIG-bench Machine Learning

Perceptual deep depth super-resolution

1 code implementation ICCV 2019 Oleg Voynov, Alexey Artemov, Vage Egiazarian, Alexander Notchenko, Gleb Bobrovskikh, Denis Zorin, Evgeny Burnaev

RGBD images, combining high-resolution color and lower-resolution depth from various types of depth sensors, are increasingly common.


ABC: A Big CAD Model Dataset For Geometric Deep Learning

3 code implementations CVPR 2019 Sebastian Koch, Albert Matveev, Zhongshi Jiang, Francis Williams, Alexey Artemov, Evgeny Burnaev, Marc Alexa, Denis Zorin, Daniele Panozzo

We introduce ABC-Dataset, a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications.

Gaussian Process Classification for Variable Fidelity Data

1 code implementation13 Sep 2018 Nikita Klyuchnikov, Evgeny Burnaev

In this paper we address a classification problem where two sources of labels with different levels of fidelity are available.

Classification General Classification

Latent Convolutional Models

1 code implementation ICLR 2019 ShahRukh Athar, Evgeny Burnaev, Victor Lempitsky

The learning process provides a latent embedding for every image in the training dataset, as well as a deep convolutional network that maps the latent space to the image space.

Colorization Image Restoration

Anonymous Walk Embeddings

2 code implementations ICML 2018 Sergey Ivanov, Evgeny Burnaev

The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data.

General Classification Graph Classification

fMRI: preprocessing, classification and pattern recognition

no code implementations26 Apr 2018 Maxim Sharaev, Alexander Andreev, Alexey Artemov, Alexander Bernstein, Evgeny Burnaev, Ekaterina Kondratyeva, Svetlana Sushchinskaya, Renat Akzhigitov

As machine learning continues to gain momentum in the neuroscience community, we witness the emergence of novel applications such as diagnostics, characterization, and treatment outcome prediction for psychiatric and neurological disorders, for instance, epilepsy and depression.

Classification General Classification

Aggregating Strategies for Long-term Forecasting

no code implementations18 Mar 2018 Alexander Korotin, Vladimir V'yugin, Evgeny Burnaev

The first one is theoretically close to an optimal algorithm and is based on replication of independent copies.

Targeted change detection in remote sensing images

no code implementations14 Mar 2018 Vladimir Ignatiev, Alexey Trekin, Viktor Lobachev, Georgy Potapov, Evgeny Burnaev

Recent developments in the remote sensing systems and image processing made it possible to propose a new method of the object classification and detection of the specific changes in the series of satellite Earth images (so called targeted change detection).

Change Detection General Classification

Driving Digital Rock towards Machine Learning: predicting permeability with Gradient Boosting and Deep Neural Networks

no code implementations2 Mar 2018 Oleg Sudakov, Evgeny Burnaev, Dmitry Koroteev

We present a research study aimed at testing of applicability of machine learning techniques for prediction of permeability of digitized rock samples.

BIG-bench Machine Learning

Satellite imagery analysis for operational damage assessment in Emergency situations

no code implementations19 Feb 2018 Alexey Trekin, German Novikov, Georgy Potapov, Vladimir Ignatiev, Evgeny Burnaev

When major disaster occurs the questions are raised how to estimate the damage in time to support the decision making process and relief efforts by local authorities or humanitarian teams.

BIG-bench Machine Learning Decision Making +2

Long-Term Online Smoothing Prediction Using Expert Advice

no code implementations8 Nov 2017 Alexander Korotin, Vladimir V'yugin, Evgeny Burnaev

In the first one, at each step $t$ the learner has to combine the point forecasts of the experts issued for the time interval $[t+1, t+d]$ ahead.

Time Series Prediction

Forecasting of commercial sales with large scale Gaussian Processes

no code implementations16 Sep 2017 Rodrigo Rivera, Evgeny Burnaev

This paper argues that there has not been enough discussion in the field of applications of Gaussian Process for the fast moving consumer goods industry.

Decision Making Gaussian Processes +1

Influence of Resampling on Accuracy of Imbalanced Classification

no code implementations12 Jul 2017 Evgeny Burnaev, Pavel Erofeev, Artem Papanov

In many real-world binary classification tasks (e. g. detection of certain objects from images), an available dataset is imbalanced, i. e., it has much less representatives of a one class (a minor class), than of another.

Classification General Classification +1

Model Selection for Anomaly Detection

no code implementations12 Jul 2017 Evgeny Burnaev, Pavel Erofeev, Dmitry Smolyakov

Anomaly detection based on one-class classification algorithms is broadly used in many applied domains like image processing (e. g. detection of whether a patient is "cancerous" or "healthy" from mammography image), network intrusion detection, etc.

Anomaly Detection Classification +3

Large Scale Variable Fidelity Surrogate Modeling

no code implementations12 Jul 2017 Evgeny Burnaev, Alexey Zaytsev

Engineers widely use Gaussian process regression framework to construct surrogate models aimed to replace computationally expensive physical models while exploring design space.

Meta-Learning for Resampling Recommendation Systems

1 code implementation6 Jun 2017 Smolyakov Dmitry, Alexander Korotin, Pavel Erofeev, Artem Papanov, Evgeny Burnaev

One possible approach to tackle the class imbalance in classification tasks is to resample a training dataset, i. e., to drop some of its elements or to synthesize new ones.

Classification General Classification +2

Steganographic Generative Adversarial Networks

1 code implementation16 Mar 2017 Denis Volkhonskiy, Ivan Nazarov, Evgeny Burnaev

Steganography is collection of methods to hide secret information ("payload") within non-secret information "container").

Large-Scale Shape Retrieval with Sparse 3D Convolutional Neural Networks

no code implementations28 Nov 2016 Alexandr Notchenko, Ermek Kapushev, Evgeny Burnaev

In this paper we present results of performance evaluation of S3DCNN - a Sparse 3D Convolutional Neural Network - on a large-scale 3D Shape benchmark ModelNet40, and measure how it is impacted by voxel resolution of input shape.

General Classification

Minimax Error of Interpolation and Optimal Design of Experiments for Variable Fidelity Data

no code implementations21 Oct 2016 Alexey Zaytsev, Evgeny Burnaev

The key question in this setting is how the sizes of the high and low fidelity data samples should be selected in order to stay within a given computational budget and maximize accuracy of the regression model prior to committing resources on data acquisition.

One-Class SVM with Privileged Information and its Application to Malware Detection

no code implementations26 Sep 2016 Evgeny Burnaev, Dmitry Smolyakov

A number of important applied problems in engineering, finance and medicine can be formulated as a problem of anomaly detection.

Anomaly Detection Classification +2

Conformalized Kernel Ridge Regression

no code implementations19 Sep 2016 Evgeny Burnaev, Ivan Nazarov

General predictive models do not provide a measure of confidence in predictions without Bayesian assumptions.

Anomaly Detection

Conformalized density- and distance-based anomaly detection in time-series data

no code implementations16 Aug 2016 Evgeny Burnaev, Vladislav Ishimtsev

Anomalies (unusual patterns) in time-series data give essential, and often actionable information in critical situations.

Anomaly Detection Intrusion Detection +1

Efficiency of conformalized ridge regression

no code implementations8 Apr 2014 Evgeny Burnaev, Vladimir Vovk

Conformal prediction is a method of producing prediction sets that can be applied on top of a wide range of prediction algorithms.

Prediction Intervals

Cannot find the paper you are looking for? You can Submit a new open access paper.