appliedAI — TransferLab

We identify, test and disseminate established and emerging techniques in machine learning in order to provide practitioners with the best tools for their applications

What we do

Trainings

Our hands-on, one to three day workshops cover fundamental and advanced topics in machine learning. We illustrate concepts with abundant real-world examples backed by rigorous theory.

Playbooks

Guided walkthroughs and industry-grade implementations of common tasks in machine learning

Reviews

In-depth analyses of the recently possible, as well as established techniques essential to the daily application of machine learning

Showcases

Visually rich, accessible explanations of novel concepts in machine learning, using open data

Software

Code libraries developed during our research and supporting our work, open sourced

Explore our work

pyDVL: the python Data Valuation Library

pyDVL strives to offer reference implementations of algorithms for data valuation with a common interface compatible with sklearn and a …

Safe and efficient deep reinforcement learning

This 2-day dive into deep RL for decision and control is suitable for engineers who want to solve real-world control problems with efficient …

Classical and modern methods in planning and control

A review of model-based planning and control for engineers interested in solving real-world decision and control problems with efficient …

Methods and issues in explainable AI

A workshop for ML practitioners wishing to make their models better understandable for themselves and decision makers.

Data valuation techniques. Applications, advances and problems

The attribution of value to data points can help in data collection, active learning, gauging model robustness, improving model performance …

Calibration of Classifiers

We discuss the calibration of probabilistic classifiers, i.e. the question of whether the output vectors of such classifiers accurately …

Read our blog

Paper Pills October 2022

What we read in October

Paper Pills September 2022

What we’ve been reading in September

Our take on IJCAI 2022

The International Joint Conference on Artificial Intelligence (IJCAI) is a premier event for researchers working in all areas of AI.

The hidden assumptions and pitfalls of density based anomaly detection

Anomaly detection is a notoriously ill-defined problem. The notion of an anomaly is arguably subjective since it depends to some extent on …

Our take on ICLR 2022 - Part 2

ICLR is one of the most important and prestigious conferences in the ML community. It spans all ML topics, from embeddings to Graph neural …

Our take on ICLR 2022 - Part 1

ICLR is one of the most important and prestigious conferences in the ML community. It spans all ML topics, from embeddings to Graph neural …

What we are reading:Paper pills

An overview and schematic comparison of recent developments in simulation-based inference and their enabling factors. Advancements in ML, Active Learning and Augmentation are named as the three driving forces in the field.

Large neural networks are very “data hungry”, but data pruning holds the promise to alleviate this dependence. A recent paper studies the use of different pruning strategies and metrics, with encouraging results.

When data samples are difficult to learn, neural networks tend to memorize their labels rather than infer useful features. This has been shown to improve, rather than limit, their accuracy. A recent paper introduces a few key concepts that help investigate this phenomenon.

BYOL was the first work to show how useful low-dimensional representations can be when learned in an unsupervised way without negative sampling. It inspired a series of simpler architectures, with SimSiam among them.

Using in-class accuracy to up-weight the value of a data point and out-of-class accuracy as a discounting factor, the authors define a new utility function that is better suited for valuation in classification tasks.

A linear gating function together with multiple expert decision trees is trained by expectation-maximization and results in a new, fully interpretable model that works well on several (simple) data sets.

Contact us

What we are reading:
Paper pills