Data efficiency
Numerous applications of Machine Learning in business intelligence, process optimization, product development or sales do not benefit from true “big data”. Blind application of state-of-the-art methods can lead to catastrophic failure. Proper data acquisition and modelling are key to successful applications.

Research feed

Pill

Resolving Training Biases via Influence-based Data Relabeling

Influence functions are used to correct corrupt labels in a dataset that would significantly decrease a trained model’s performance. …

Fabio Peruzzo
Data Efficiency
Seminar

An introduction to Unsupervised Neural Machine Translation

Lack of large parallel corpora or dictionaries for most language pairs and modern data-hungry models make the need for unsupervised …

Sebastian Wagner
Data Efficiency
Seminar

Dealing with imbalanced classes

In this talk Wolfgang shares some of his personal experience and methods while training classifier CNNs on image datasets with highly …

Wolfgang Reuter
Data Efficiency
Seminar

Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning

Paper abstract: Model-free deep reinforcement learning algorithms have been shown to be capable of learning a wide range of robotic skills, …

Fabian Hainzl
Data Efficiency
Reinforcement Learning
Seminar

A short introduction to model-based Reinforcement Learning

Model-based RL learns a deterministic or probabilistic forward model of the dynamics of an environment for action planning or direct policy …

Miguel de Benito Delgado
Data Efficiency
Reinforcement Learning
Seminar

An introduction to data distillation

Distillation ensembles predictions from multiple transformations of unlabeled data, using a single model, to automatically generate new …

Ishmeet Kaur
Data Efficiency

Other series in Efficient Machine Learning

Data valuation

Attributions of value to training samples can be used to examine data, improve data acquisition, debug and improve models or compensate data …

Efficient Machine Learning
Check all of our work