Alexandre Abrahamindata from the trenchesOpenAL: Evaluation and Interpretation of Active Learning StrategiesWe are pleased to present our work accepted at the NeurIPS 2022 Workshop on Human in the Loop Learning! For a complete overview of our…3 min read·Dec 5, 2022----
Alexandre Abrahamindata from the trenchesTowards Efficient Labeling in Federated LearningFederated Learning (FL) can enable privacy-preserving distributed computation across several clients. It is used to federate knowledge…7 min read·Nov 10, 2022--2--2
Alexandre Abrahamindata from the trenchesDiversity in Outcome Optimization of ML ModelsML outcome optimization is the process of finding optimal feature values that give the model prediction minimum (or maximum) over a defined…8 min read·Jun 2, 2022----
Alexandre Abrahamindata from the trenchesI Can’t Believe It’s Not Better — Active Learning FlavorThis is the story of a research project that didn’t quite make it. We introduce a new active learning strategy and put it to the test.9 min read·Jun 10, 2021--1--1
Alexandre Abrahamindata from the trenchesA (Slightly) Better Budget Allocation for HyperbandRounding operations can lead Hyperband not to use 7% of the available budget. We propose a method that reduces unused budget to 3%.10 min read·Apr 30, 2020----
Alexandre Abrahamindata from the trenchesDiverse Mini-Batch Active Learning: A Reproduction ExerciseLessons learned from reproducing “Diverse Mini-Batch Active Learning”, a strategy mixing uncertainty and diversity techniques.9 min read·Mar 12, 2020--4--4
Alexandre Abrahamindata from the trenchesA Proactive Look at Active Learning PackagesIntroduction to Active Learning through a quick benchmark of major Python packages: modAL, libact, and alipy.14 min read·Feb 20, 2020----
