
Mill.jl and JsonGrinder.jl: automated differentiable feature extraction for learning from raw JSON data
Learning from raw data input, thus limiting the need for manual feature ...
read it

Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks
Even though machine learning algorithms already play a significant role ...
read it

Comparison of Anomaly Detectors: Context Matters
Deep generative models are challenging the classical methods in the fiel...
read it

Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks
We present a novel deep reinforcement learning framework for solving rel...
read it

Neural Power Units
Conventional Neural Networks can approximate simple arithmetic operation...
read it

SumProductTransform Networks: Exploiting Symmetries using Invertible Transformations
In this work, we propose SumProductTransform Networks (SPTN), an exten...
read it

General Framework for Binary Classification on Top Samples
Many binary classification problems minimize misclassification above (or...
read it

Nested Multiple Instance Learning in Modelling of HTTP network traffic
In many interesting cases, the application of machine learning is hinder...
read it

Rodent: Relevance determination in ODE
From a set of observed trajectories of a partially observed system, we a...
read it

Deep Reinforcement Learning with Explicitly Represented Knowledge and Variable State and Action Spaces
We focus on a class of realworld domains, where gathering hierarchical ...
read it

Classification with Costly Features as a Sequential DecisionMaking Problem
This work focuses on a specific classification problem, where the inform...
read it

Joint Detection of Malicious Domains and Infected Clients
Detection of malwareinfected computers and detection of malicious web d...
read it

Approximation capability of neural networks on spaces of probability measures and treestructured domains
This paper extends the proof of density of neural networks in the space ...
read it

Anomaly scores for generative models
Reconstruction error is a prevalent score used to identify anomalous sam...
read it

Are generative deep models for novelty detection truly better?
Many deep models have been recently proposed for anomaly detection. This...
read it

Algorithms for solving optimization problems arising from deep neural net models: nonsmooth problems
Machine Learning models incorporating multiple layered learning networks...
read it

Algorithms for solving optimization problems arising from deep neural net models: smooth problems
Machine Learning models incorporating multiple layered learning networks...
read it

Classification with Costly Features using Deep Reinforcement Learning
We study a classification problem where each feature can be acquired for...
read it

Using Neural Network Formalism to Solve MultipleInstance Problems
Many objects in the real world are difficult to describe by a single num...
read it
Tomáš Pevný
is this you? claim profile