380 citations · 1.1k across the 15 of their papers we have counts for
16 papers
Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?
Balázs Kégl, Gabriel Hurtado, Albert Thomas
We contribute to micro-data model-based reinforcement learning (MBRL) by rigorously comparing popular generative models using a fixed (random shooting) control agent. We find that…
InsectUp: Crowdsourcing Insect Observations to Assess Demographic Shifts and Improve Classification
Léonard Boussioux, Tomás Giro-Larraz, Charles Guille-Escuret +2
Insects play such a crucial role in ecosystems that a shift in demography of just a few species can have devastating consequences at environmental, social and economic levels. Desp…
Spurious samples in deep generative models: bug or feature?
Balázs Kégl, Mehdi Cherti, Akın Kazakçı
Traditional wisdom in generative modeling literature is that spurious samples that a model can generate are errors and they should be avoided. Recent research, however, has shown i…
Similarity encoding for learning with dirty categorical variables
Patricio Cerda, Gaël Varoquaux, Balázs Kégl
For statistical learning, categorical variables in a table are usually considered as discrete entities and encoded separately to feature vectors, e.g., with one-hot encoding. "Dirt…
Machine learning for classification and quantification of monoclonal antibody preparations for cancer therapy
Laetitia Le, Camille Marini, Alexandre Gramfort +9
Monoclonal antibodies constitute one of the most important strategies to treat patients suffering from cancers such as hematological malignancies and solid tumors. In order to guar…
Digits that are not: Generating new types through deep neural nets
Akın Kazakçıand Mehdi Cherti, Balázs Kégl
For an artificial creative agent, an essential driver of the search for novelty is a value function which is often provided by the system designer or users. We argue that an import…