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

Review Partner area

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 …

Data Valuation

May 15, 2021

Review Partner area

Calibration of Classifiers

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

Classifier Calibration

Apr 29, 2021

Software

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 …

Data Valuation

Apr 3, 2021

Training

Calibration of modern classifiers

An introduction to the pitfalls of uncalibrated classifiers and modern techniques for (re)calibration.

Read our blog

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 …

May 10, 2022

Certified error rates for neural networks

Adversarial training has been shown to improve robustness of neural networks to certain classes of data perturbations. Despite constant …

Robustness in ML

Jan 14, 2022

Natural, Trust Region and Proximal Policy Optimization

We present an overview of the theory behind three popular and related algorithms for gradient based policy optimization: natural policy …

Efficient RL

Aug 10, 2021

Cross-validation: what does it estimate?

In Cross-validation: what does it estimate and how well does it do it? Bates et al. focus on cross validation for error estimation and show …

Error Estimation and Model Selection

Jun 11, 2021

What we are reading:
Paper pills

Natural Posterior Networks

Jun 29, 2022

This paper proposes a new way to train neural networks with exponential family posterior uncertainty estimates.

Bayesian Methods

Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy

Jun 26, 2022

This paper proposes a new anomaly detection approach on time series. They employ a new minimax optimization scheme to learn complex and long range association between the points in a time series. They hypothesize that nominal points should be well reconstructed from such associations but anomalies shouldn’t due to their erratic nature.

Anomaly Detection

Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems

Jun 26, 2022

This paper proposes a new algorithm, curvatureEG+, that converges for a broader range of weak minty variational inequalities.

Graph Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series

Jun 26, 2022

This paper proposes a new method for simultaneous anomaly detection on several time series. They learn the structure of a Bayesian network to model the dependencies between the time series and use a graph neural network on the dependency structure to compute the input for a conditional normalizing flow that reconstructs the next point for each series.

Anomaly Detection

GraphML

GreaseLM: Graph REASoning Enhanced Language Models

Jun 26, 2022

This paper proposes to combine the capabilities of large language models and massive knowledge graphs. Novel to their approach is the layer-wise interaction between the language model and the graph neural network on the knowledge graph.

GraphML

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

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 …

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 …

Calibration of modern classifiers

An introduction to the pitfalls of uncalibrated classifiers and modern techniques for (re)calibration.

Read our blog

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 …

Certified error rates for neural networks

Adversarial training has been shown to improve robustness of neural networks to certain classes of data perturbations. Despite constant …

Natural, Trust Region and Proximal Policy Optimization

We present an overview of the theory behind three popular and related algorithms for gradient based policy optimization: natural policy …

Cross-validation: what does it estimate?

In Cross-validation: what does it estimate and how well does it do it? Bates et al. focus on cross validation for error estimation and show …

What we are reading:Paper pills

This paper proposes a new way to train neural networks with exponential family posterior uncertainty estimates.

This paper proposes a new algorithm, curvatureEG+, that converges for a broader range of weak minty variational inequalities.

This paper proposes to combine the capabilities of large language models and massive knowledge graphs. Novel to their approach is the layer-wise interaction between the language model and the graph neural network on the knowledge graph.

Contact us

What we are reading:
Paper pills