Search Results for author: Jacek Tabor

Found 55 papers, 24 papers with code

ProPaLL: Probabilistic Partial Label Learning

no code implementations21 Aug 2022 Łukasz Struski, Jacek Tabor, Bartosz Zieliński

Partial label learning is a type of weakly supervised learning, where each training instance corresponds to a set of candidate labels, among which only one is true.

Partial Label Learning

LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood

1 code implementation ICLR Workshop GTRL 2021 Piotr Tempczyk, Rafał Michaluk, Łukasz Garncarek, Przemysław Spurek, Jacek Tabor, Adam Goliński

We attempt to address that challenge by proposing a novel approach to the problem: Local Intrinsic Dimension estimation using approximate Likelihood (LIDL).

Density Estimation

SLOVA: Uncertainty Estimation Using Single Label One-Vs-All Classifier

no code implementations28 Jun 2022 Bartosz Wójcik, Jacek Grela, Marek Śmieja, Krzysztof Misztal, Jacek Tabor

The proposed classifier is confident only if a single class has a high probability and other probabilities are negligible.

Bounding Evidence and Estimating Log-Likelihood in VAE

no code implementations19 Jun 2022 Łukasz Struski, Marcin Mazur, Paweł Batorski, Przemysław Spurek, Jacek Tabor

Many crucial problems in deep learning and statistics are caused by a variational gap, i. e., a difference between evidence and evidence lower bound (ELBO).

Continual Learning with Guarantees via Weight Interval Constraints

1 code implementation16 Jun 2022 Maciej Wołczyk, Karol J. Piczak, Bartosz Wójcik, Łukasz Pustelnik, Paweł Morawiecki, Jacek Tabor, Tomasz Trzciński, Przemysław Spurek

We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting.

Continual Learning

MisConv: Convolutional Neural Networks for Missing Data

1 code implementation26 Oct 2021 Marcin Przewięźlikowski, Marek Śmieja, Łukasz Struski, Jacek Tabor

Processing of missing data by modern neural networks, such as CNNs, remains a fundamental, yet unsolved challenge, which naturally arises in many practical applications, like image inpainting or autonomous vehicles and robots.

Image Inpainting Imputation

Relative Molecule Self-Attention Transformer

no code implementations12 Oct 2021 Łukasz Maziarka, Dawid Majchrowski, Tomasz Danel, Piotr Gaiński, Jacek Tabor, Igor Podolak, Paweł Morkisz, Stanisław Jastrzębski

Self-supervised learning holds promise to revolutionize molecule property prediction - a central task to drug discovery and many more industries - by enabling data efficient learning from scarce experimental data.

Drug Discovery Self-Supervised Learning

Flow-based SVDD for anomaly detection

no code implementations10 Aug 2021 Marcin Sendera, Marek Śmieja, Łukasz Maziarka, Łukasz Struski, Przemysław Spurek, Jacek Tabor

We propose FlowSVDD -- a flow-based one-class classifier for anomaly/outliers detection that realizes a well-known SVDD principle using deep learning tools.

Anomaly Detection One-class classifier

SONG: Self-Organizing Neural Graphs

no code implementations28 Jul 2021 Łukasz Struski, Tomasz Danel, Marek Śmieja, Jacek Tabor, Bartosz Zieliński

Recent years have seen a surge in research on deep interpretable neural networks with decision trees as one of the most commonly incorporated tools.

Direction is what you need: Improving Word Embedding Compression in Large Language Models

1 code implementation ACL (RepL4NLP) 2021 Klaudia Bałazy, Mohammadreza Banaei, Rémi Lebret, Jacek Tabor, Karl Aberer

The adoption of Transformer-based models in natural language processing (NLP) has led to great success using a massive number of parameters.

Language Modelling

Zero Time Waste: Recycling Predictions in Early Exit Neural Networks

1 code implementation NeurIPS 2021 Maciej Wołczyk, Bartosz Wójcik, Klaudia Bałazy, Igor Podolak, Jacek Tabor, Marek Śmieja, Tomasz Trzciński

The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications.

RegFlow: Probabilistic Flow-based Regression for Future Prediction

no code implementations30 Nov 2020 Maciej Zięba, Marcin Przewięźlikowski, Marek Śmieja, Jacek Tabor, Tomasz Trzcinski, Przemysław Spurek

Predicting future states or actions of a given system remains a fundamental, yet unsolved challenge of intelligence, especially in the scope of complex and non-deterministic scenarios, such as modeling behavior of humans.

Future prediction

ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery

no code implementations29 Nov 2020 Dawid Rymarczyk, Łukasz Struski, Jacek Tabor, Bartosz Zieliński

In this paper, we introduce ProtoPShare, a self-explained method that incorporates the paradigm of prototypical parts to explain its predictions.

Classification General Classification +1

Generative models with kernel distance in data space

1 code implementation15 Sep 2020 Szymon Knop, Marcin Mazur, Przemysław Spurek, Jacek Tabor, Igor Podolak

First, an autoencoder based architecture, using kernel measures, is built to model a manifold of data.

Adversarial Examples Detection and Analysis with Layer-wise Autoencoders

no code implementations17 Jun 2020 Bartosz Wójcik, Paweł Morawiecki, Marek Śmieja, Tomasz Krzyżek, Przemysław Spurek, Jacek Tabor

We present a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network.

HyperFlow: Representing 3D Objects as Surfaces

1 code implementation15 Jun 2020 Przemysław Spurek, Maciej Zięba, Jacek Tabor, Tomasz Trzciński

To that end, we devise a generative model that uses a hypernetwork to return the weights of a Continuous Normalizing Flows (CNF) target network.

Autonomous Driving Quantization

Kernel Self-Attention in Deep Multiple Instance Learning

no code implementations25 May 2020 Dawid Rymarczyk, Adriana Borowa, Jacek Tabor, Bartosz Zieliński

There have been several attempts to create a model working with a bag of instances, however, they are assuming that there are no dependencies within the bag and the label is connected to at least one instance.

Multiple Instance Learning whole slide images

Finding the Optimal Network Depth in Classification Tasks

1 code implementation17 Apr 2020 Bartosz Wójcik, Maciej Wołczyk, Klaudia Bałazy, Jacek Tabor

We develop a fast end-to-end method for training lightweight neural networks using multiple classifier heads.

Classification General Classification

The Break-Even Point on Optimization Trajectories of Deep Neural Networks

no code implementations ICLR 2020 Stanislaw Jastrzebski, Maciej Szymczak, Stanislav Fort, Devansh Arpit, Jacek Tabor, Kyunghyun Cho, Krzysztof Geras

We argue for the existence of the "break-even" point on this trajectory, beyond which the curvature of the loss surface and noise in the gradient are implicitly regularized by SGD.

Molecule Attention Transformer

4 code implementations19 Feb 2020 Łukasz Maziarka, Tomasz Danel, Sławomir Mucha, Krzysztof Rataj, Jacek Tabor, Stanisław Jastrzębski

Designing a single neural network architecture that performs competitively across a range of molecule property prediction tasks remains largely an open challenge, and its solution may unlock a widespread use of deep learning in the drug discovery industry.

Drug Discovery

LocoGAN -- Locally Convolutional GAN

1 code implementation18 Feb 2020 Łukasz Struski, Szymon Knop, Jacek Tabor, Wiktor Daniec, Przemysław Spurek

In the paper we construct a fully convolutional GAN model: LocoGAN, which latent space is given by noise-like images of possibly different resolutions.

Hypernetwork approach to generating point clouds

2 code implementations ICML 2020 Przemysław Spurek, Sebastian Winczowski, Jacek Tabor, Maciej Zamorski, Maciej Zięba, Tomasz Trzciński

The main idea of our HyperCloud method is to build a hyper network that returns weights of a particular neural network (target network) trained to map points from a uniform unit ball distribution into a 3D shape.

Generating 3D Point Clouds

WICA: nonlinear weighted ICA

1 code implementation13 Jan 2020 Andrzej Bedychaj, Przemysław Spurek, Aleksandra Nowak, Jacek Tabor

Independent Component Analysis (ICA) aims to find a coordinate system in which the components of the data are independent.

Biologically-Inspired Spatial Neural Networks

no code implementations NeurIPS Workshop Neuro_AI 2019 Maciej Wołczyk, Jacek Tabor, Marek Śmieja, Szymon Maszke

We introduce bio-inspired artificial neural networks consisting of neurons that are additionally characterized by spatial positions.

Continual Learning

Spatial Graph Convolutional Networks

1 code implementation11 Sep 2019 Tomasz Danel, Przemysław Spurek, Jacek Tabor, Marek Śmieja, Łukasz Struski, Agnieszka Słowik, Łukasz Maziarka

Graph Convolutional Networks (GCNs) have recently become the primary choice for learning from graph-structured data, superseding hash fingerprints in representing chemical compounds.

Image Classification

SeGMA: Semi-Supervised Gaussian Mixture Auto-Encoder

no code implementations21 Jun 2019 Marek Śmieja, Maciej Wołczyk, Jacek Tabor, Bernhard C. Geiger

We propose a semi-supervised generative model, SeGMA, which learns a joint probability distribution of data and their classes and which is implemented in a typical Wasserstein auto-encoder framework.

Style Transfer

Fast and Stable Interval Bounds Propagation for Training Verifiably Robust Models

1 code implementation3 Jun 2019 Paweł Morawiecki, Przemysław Spurek, Marek Śmieja, Jacek Tabor

We present an efficient technique, which allows to train classification networks which are verifiably robust against norm-bounded adversarial attacks.

Independent Component Analysis based on multiple data-weighting

no code implementations31 May 2019 Andrzej Bedychaj, Przemysław Spurek, Łukasz Struskim, Jacek Tabor

Independent Component Analysis (ICA) - one of the basic tools in data analysis - aims to find a coordinate system in which the components of the data are independent.

Realism Index: Interpolation in Generative Models With Arbitrary Prior

no code implementations6 Apr 2019 Łukasz Struski, Jacek Tabor, Igor Podolak, Aleksandra Nowak, Krzysztof Maziarz

In order to perform plausible interpolations in the latent space of a generative model, we need a measure that credibly reflects if a point in an interpolation is close to the data manifold being modelled, i. e. if it is convincing.

Non-linear ICA based on Cramer-Wold metric

no code implementations1 Mar 2019 Przemysław Spurek, Aleksandra Nowak, Jacek Tabor, Łukasz Maziarka, Stanisław Jastrzębski

Non-linear source separation is a challenging open problem with many applications.

Hypernetwork functional image representation

no code implementations27 Feb 2019 Sylwester Klocek, Łukasz Maziarka, Maciej Wołczyk, Jacek Tabor, Jakub Nowak, Marek Śmieja

Motivated by the human way of memorizing images we introduce their functional representation, where an image is represented by a neural network.

Image Super-Resolution

LOSSGRAD: automatic learning rate in gradient descent

1 code implementation20 Feb 2019 Bartosz Wójcik, Łukasz Maziarka, Jacek Tabor

In this paper, we propose a simple, fast and easy to implement algorithm LOSSGRAD (locally optimal step-size in gradient descent), which automatically modifies the step-size in gradient descent during neural networks training.

Sliced generative models

no code implementations29 Jan 2019 Szymon Knop, Marcin Mazur, Jacek Tabor, Igor Podolak, Przemysław Spurek

In this paper we discuss a class of AutoEncoder based generative models based on one dimensional sliced approach.

Set Aggregation Network as a Trainable Pooling Layer

1 code implementation3 Oct 2018 Łukasz Maziarka, Marek Śmieja, Aleksandra Nowak, Jacek Tabor, Łukasz Struski, Przemysław Spurek

Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data.

Deep processing of structured data

no code implementations27 Sep 2018 Łukasz Maziarka, Marek Śmieja, Aleksandra Nowak, Jacek Tabor, Łukasz Struski, Przemysław Spurek

We construct a general unified framework for learning representation of structured data, i. e. data which cannot be represented as the fixed-length vectors (e. g. sets, graphs, texts or images of varying sizes).

Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function

no code implementations24 Sep 2018 Wojciech Tarnowski, Piotr Warchoł, Stanisław Jastrzębski, Jacek Tabor, Maciej A. Nowak

We propose that in ResNets this can be resolved based on our results, by ensuring the same level of dynamical isometry at initialization.

Cramer-Wold AutoEncoder

2 code implementations ICLR 2019 Szymon Knop, Jacek Tabor, Przemysław Spurek, Igor Podolak, Marcin Mazur, Stanisław Jastrzębski

The crucial new ingredient is the introduction of a new (Cramer-Wold) metric in the space of densities, which replaces the Wasserstein metric used in SWAE.

Processing of missing data by neural networks

1 code implementation NeurIPS 2018 Marek Smieja, Łukasz Struski, Jacek Tabor, Bartosz Zieliński, Przemysław Spurek

We propose a general, theoretically justified mechanism for processing missing data by neural networks.


Cascade context encoder for improved inpainting

no code implementations11 Mar 2018 Bartosz Zieliński, Łukasz Struski, Marek Śmieja, Jacek Tabor

For this purpose, we train context encoder for 64x64 pixels images in a standard way and use its resized output to fill in the missing input region of the 128x128 context encoder, both in training and evaluation phase.

Efficient mixture model for clustering of sparse high dimensional binary data

1 code implementation11 Jul 2017 Marek Śmieja, Krzysztof Hajto, Jacek Tabor

In this paper we propose a mixture model, SparseMix, for clustering of sparse high dimensional binary data, which connects model-based with centroid-based clustering.

Semi-supervised model-based clustering with controlled clusters leakage

no code implementations4 May 2017 Marek Śmieja, Łukasz Struski, Jacek Tabor

In this paper, we focus on finding clusters in partially categorized data sets.

Spherical Wards clustering and generalized Voronoi diagrams

no code implementations4 May 2017 Marek Śmieja, Jacek Tabor

In order to graphically represent and interpret the results the notion of Voronoi diagram was generalized to non Euclidean spaces and applied for introduced clustering method.

Pointed subspace approach to incomplete data

no code implementations2 May 2017 Łukasz Struski, Marek Śmieja, Jacek Tabor

Incomplete data are often represented as vectors with filled missing attributes joined with flag vectors indicating missing components.

Dimensionality Reduction General Classification

Generalized RBF kernel for incomplete data

no code implementations5 Dec 2016 Łukasz Struski, Marek Śmieja, Jacek Tabor

We construct $\bf genRBF$ kernel, which generalizes the classical Gaussian RBF kernel to the case of incomplete data.

Introduction to Cross-Entropy Clustering The R Package CEC

no code implementations19 Aug 2015 Jacek Tabor, Przemysław Spurek, Konrad Kamieniecki, Marek Śmieja, Krzysztof Misztal

The R Package CEC performs clustering based on the cross-entropy clustering (CEC) method, which was recently developed with the use of information theory.

Maximum Entropy Linear Manifold for Learning Discriminative Low-dimensional Representation

no code implementations10 Apr 2015 Wojciech Marian Czarnecki, Rafał Józefowicz, Jacek Tabor

Representation learning is currently a very hot topic in modern machine learning, mostly due to the great success of the deep learning methods.

Data Visualization Dimensionality Reduction +2

Extreme Entropy Machines: Robust information theoretic classification

no code implementations21 Jan 2015 Wojciech Marian Czarnecki, Jacek Tabor

The main contribution of this paper is proposing a model based on the information theoretic concepts which on the one hand shows new, entropic perspective on known linear classifiers and on the other leads to a construction of very robust method competetitive with the state of the art non-information theoretic ones (including Support Vector Machines and Extreme Learning Machines).

Classification General Classification

Cluster based RBF Kernel for Support Vector Machines

no code implementations12 Aug 2014 Wojciech Marian Czarnecki, Jacek Tabor

In the classical Gaussian SVM classification we use the feature space projection transforming points to normal distributions with fixed covariance matrices (identity in the standard RBF and the covariance of the whole dataset in Mahalanobis RBF).

General Classification

Multithreshold Entropy Linear Classifier

no code implementations4 Aug 2014 Wojciech Marian Czarnecki, Jacek Tabor

Then we prove that our method is a multithreshold large margin classifier, which shows the analogy to the SVM, while in the same time works with much broader class of hypotheses.

Activity Prediction

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