11 citations · 18 across the 7 of their papers we have counts for
7 papers
Non-linear PCA via Evolution Strategies: a Novel Objective Function
Thomas Uriot, Elise Chung
Principal Component Analysis (PCA) is a powerful and popular dimensionality reduction technique. However, due to its linear nature, it often fails to capture the complex underlying…
On Debiasing Text Embeddings Through Context Injection
Thomas Uriot
Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications re…
On genetic programming representations and fitness functions for interpretable dimensionality reduction
Thomas Uriot, Marco Virgolin, Tanja Alderliesten +1
Dimensionality reduction (DR) is an important technique for data exploration and knowledge discovery. However, most of the main DR methods are either linear (e.g., PCA), do not pro…
Spacecraft Collision Avoidance Challenge: design and results of a machine learning competition
Thomas Uriot, Dario Izzo, Luís F. Sim{õ}es +7
Spacecraft collision avoidance procedures have become an essential part of satellite operations. Complex and constantly updated estimates of the collision risk between orbiting obj…
Safe Crossover of Neural Networks Through Neuron Alignment
Thomas Uriot, Dario Izzo
One of the main and largely unexplored challenges in evolving the weights of neural networks using genetic algorithms is to find a sensible crossover operation between parent netwo…
Kernel Mean Embedding of Instance-wise Predictions in Multiple Instance Regression
Thomas Uriot
In this paper, we propose an extension to an existing algorithm (instance-MIR) which tackles the multiple instance regression (MIR) problem, also known as distribution regression.…
Learning with Sets in Multiple Instance Regression Applied to Remote Sensing
Thomas Uriot
In this paper, we propose a novel approach to tackle the multiple instance regression (MIR) problem. This problem arises when the data is a collection of bags, where each bag is ma…