Open in app
Sign inGet started
Paired Open-Ended Trailblazer (POET)

Paired Open-Ended Trailblazer (POET)

Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
Go to the profile of Jaroslav Urban
Jaroslav Urban
Center and Scale Prediction for pedestrian detection

Center and Scale Prediction for pedestrian detection

This post is focused on the problem of computer vision called pedestrian detection, looks at three families of the pedestrian detection…
Go to the profile of Adam Jirovský
Adam Jirovský
BERT: Google’s bidirectional transformer

BERT: Google’s bidirectional transformer

It is commonly known that machine translation, text summarization or other natural language processing (NLP) tasks are quite challenging…
Go to the profile of Jan Perina
Jan Perina
Evaluating Probabilistic Classifier: ROC and PR(G) Curves

Evaluating Probabilistic Classifier: ROC and PR(G) Curves

Evaluation of classification performance commonly shrinks to reporting accuracy, precision, recall or F1 scores. However, these metrics do…
Go to the profile of Jan Lukány
Jan Lukány
Data augmentation using GAN

Data augmentation using GAN

Machine learning models require for their training a vast amount of data that we not always have. One possible solution would be to…
Go to the profile of Iveta Šárfyová
Iveta Šárfyová
Context Encoder — Image inpainting using GAN

Context Encoder — Image inpainting using GAN

Context Encoder [1] is an architecture used for image inpainting, which has proved to have a high potential and was used as a foundation…
Go to the profile of Tomáš Halama
Tomáš Halama
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space

Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space

Attempt to explain PPGN in 15 minutes or less
Go to the profile of Jan Maděra
Jan Maděra
About knowledge-engineering-seminarLatest StoriesArchiveAbout MediumTermsPrivacyTeams