4 papers
Data Mining-Based Techniques for Software Fault Localization
Peggy Cellier, Mireille Ducassé, Sébastien Ferré +2
This chapter illustrates the basic concepts of fault localization using a data mining technique. It utilizes the Trityp program to illustrate the general method. Formal concept ana…
MADIL: An MDL-based Framework for Efficient Program Synthesis in the ARC Benchmark
Sébastien Ferré
Artificial Intelligence (AI) has achieved remarkable success in specialized tasks but struggles with efficient skill acquisition and generalization. The Abstraction and Reasoning C…
Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principle
Sébastien Ferré
The Abstraction and Reasoning Corpus (ARC) is a challenging benchmark, introduced to foster AI research towards human-level intelligence. It is a collection of unique tasks about g…
Output-weighted and relative entropy loss functions for deep learning precursors of extreme events
Samuel Rudy, Themistoklis Sapsis
Many scientific and engineering problems require accurate models of dynamical systems with rare and extreme events. Such problems present a challenging task for data-driven modelli…