Conditional GANs are frequently used for manipulating the attributes of face images, such as expression, hairstyle, pose, or age.
Graph Neural Networks (GNNs) play a fundamental role in many deep learning problems, in particular in cheminformatics.
By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo are able to reach quality on par with supervised approaches.
We evaluated HyperTab on more than 40 tabular datasets of a varying number of samples and domains of origin, and compared its performance with shallow and deep learning models representing the current state-of-the-art.
Deep clustering has been dominated by flat models, which split a dataset into a predefined number of groups.
Ranked #1 on Image Clustering on MNIST
The proposed classifier is confident only if a single class has a high probability and other probabilities are negligible.
Although this setting is natural for biological systems, it proves very difficult for machine learning models such as artificial neural networks.
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.
Structural fingerprints and pharmacophore modeling are methodologies that have been used for at least two decades in various fields of cheminformatics: from similarity searching to machine learning (ML).
Modern generative models achieve excellent quality in a variety of tasks including image or text generation and chemical molecule modeling.
We propose FlowSVDD -- a flow-based one-class classifier for anomaly/outliers detection that realizes a well-known SVDD principle using deep learning tools.
Recent years have seen a surge in research on deep interpretable neural networks with decision trees as one of the most commonly incorporated tools.
The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications.
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.
We investigate the problem of training neural networks from incomplete images without replacing missing values.
We propose OneFlow - a flow-based one-class classifier for anomaly (outlier) detection that finds a minimal volume bounding region.
We consider the problem of estimating the conditional probability distribution of missing values given the observed ones.
We present a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network.
This paper introduces an approach to filling in missing data based on deep auto-encoder models, adequate to high-dimensional data exhibiting complex dependencies, such as images.
In this paper, we introduce a neural network framework for semi-supervised clustering (SSC) with pairwise (must-link or cannot-link) constraints.
Graph Convolutional Networks (GCNs) have recently become the primary choice for learning from graph-structured data, superseding hash fingerprints in representing chemical compounds.
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.
We present an efficient technique, which allows to train classification networks which are verifiably robust against norm-bounded adversarial attacks.
Motivated by the human way of memorizing images we introduce their functional representation, where an image is represented by a neural network.
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.
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).
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.
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.
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.
By combining the ideas from cross-entropy clustering (CEC) with those from the information bottleneck method (IB), our method trades between three conflicting goals: the accuracy with which the data set is modeled, the simplicity of the model, and the consistency of the clustering with side information.
Incomplete data are often represented as vectors with filled missing attributes joined with flag vectors indicating missing components.
The R Package CEC performs clustering based on the cross-entropy clustering (CEC) method, which was recently developed with the use of information theory.