Search Results for author: Simon Mandlik

Found 2 papers, 1 papers with code

Mill.jl and JsonGrinder.jl: automated differentiable feature extraction for learning from raw JSON data

4 code implementations19 May 2021 Simon Mandlik, Matej Racinsky, Viliam Lisy, Tomas Pevny

Learning from raw data input, thus limiting the need for manual feature engineering, is one of the key components of many successful applications of machine learning methods.

BIG-bench Machine Learning Feature Engineering

Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks

no code implementations19 Apr 2021 Simon Mandlik, Tomas Pevny

Even though machine learning algorithms already play a significant role in data science, many current methods pose unrealistic assumptions on input data.

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