
Flowbased SVDD for anomaly detection
We propose FlowSVDD – a flowbased oneclass classifier for anomaly/outl...
read it

SONG: SelfOrganizing Neural Graphs
Recent years have seen a surge in research on deep interpretable neural ...
read it

Direction is what you need: Improving Word Embedding Compression in Large Language Models
The adoption of Transformerbased models in natural language processing ...
read it

Zero Time Waste: Recycling Predictions in Early Exit Neural Networks
The problem of reducing processing time of large deep learning models is...
read it

HyperPocket: Generative Point Cloud Completion
Scanning reallife scenes with modern registration devices typically giv...
read it

RegFlow: Probabilistic Flowbased Regression for Future Prediction
Predicting future states or actions of a given system remains a fundamen...
read it

ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery
In this paper, we introduce ProtoPShare, a selfexplained method that in...
read it

Flowbased anomaly detection
We propose OneFlow  a flowbased oneclass classifier for anomaly (outl...
read it

Generative models with kernel distance in data space
Generative models dealing with modeling a joint data distribution are ge...
read it

Adversarial Examples Detection and Analysis with Layerwise Autoencoders
We present a mechanism for detecting adversarial examples based on data ...
read it

HyperFlow: Representing 3D Objects as Surfaces
In this work, we present HyperFlow  a novel generative model that lever...
read it

Kernel SelfAttention in Deep Multiple Instance Learning
Multiple Instance Learning (MIL) is weakly supervised learning, which as...
read it

Finding the Optimal Network Depth in Classification Tasks
We develop a fast endtoend method for training lightweight neural netw...
read it

The BreakEven Point on Optimization Trajectories of Deep Neural Networks
The early phase of training of deep neural networks is critical for thei...
read it

Molecule Attention Transformer
Designing a single neural network architecture that performs competitive...
read it

LocoGAN – Locally Convolutional GAN
In the paper we construct a fully convolutional GAN model: LocoGAN, whic...
read it

WICA: nonlinear weighted ICA
Independent Component Analysis (ICA) aims to find a coordinate system in...
read it

BiologicallyInspired Spatial Neural Networks
We introduce bioinspired artificial neural networks consisting of neuro...
read it

Geometric Graph Convolutional Neural Networks
Graph Convolutional Networks (GCNs) have recently become the primary cho...
read it

SeGMA: SemiSupervised Gaussian Mixture AutoEncoder
We propose a semisupervised generative model, SeGMA, which learns a joi...
read it

Fast and Stable Interval Bounds Propagation for Training Verifiably Robust Models
We present an efficient technique, which allows to train classification ...
read it

Independent Component Analysis based on multiple dataweighting
Independent Component Analysis (ICA)  one of the basic tools in data an...
read it

Oneelement Batch Training by Moving Window
Several deep models, esp. the generative, compare the samples from two d...
read it

Interpolation in generative models
We show how to construct smooth and realistic interpolations for generat...
read it

Nonlinear ICA based on CramerWold metric
Nonlinear source separation is a challenging open problem with many app...
read it

Multitask hypernetworks
Hypernetworks mechanism allows to generate and train neural networks (ta...
read it

LOSSGRAD: automatic learning rate in gradient descent
In this paper, we propose a simple, fast and easy to implement algorithm...
read it

Sliced generative models
In this paper we discuss a class of AutoEncoder based generative models ...
read it

Deep processing of structured data
We construct a general unified framework for learning representation of ...
read it

Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function
We demonstrate that in residual neural networks (ResNets) dynamical isom...
read it

CramerWold AutoEncoder
We propose a new generative model, CramerWold Autoencoder (CWAE). Follo...
read it

Processing of missing data by neural networks
We propose a general, theoretically justified mechanism for processing m...
read it

Cascade context encoder for improved inpainting
In this paper, we analyze if cascade usage of the context encoder with i...
read it

Efficient mixture model for clustering of sparse high dimensional binary data
In this paper we propose a mixture model, SparseMix, for clustering of s...
read it

Semisupervised modelbased clustering with controlled clusters leakage
In this paper, we focus on finding clusters in partially categorized dat...
read it

Introduction to CrossEntropy Clustering The R Package CEC
The R Package CEC performs clustering based on the crossentropy cluster...
read it

Multithreshold Entropy Linear Classifier
Linear classifiers separate the data with a hyperplane. In this paper we...
read it

Detection of elliptical shapes via crossentropy clustering
The problem of finding elliptical shapes in an image will be considered....
read it
Jacek Tabor
is this you? claim profile