MATH-700 / 3 crédits

Enseignant: Abbé Emmanuel

Langue: Anglais

Remark: Fall 2025. The class discusses theoretical and applied developments on AI reasoning; the main class output is an experimental project (including typically training/finetuning of foundation models)


Frequency

Every year

Summary

Large language models have raised the potential of artificial intelligence in various applications, including science and mathematics, but their reasoning capabilities remain under investigations. This class focuses on defining, measuring and improving the reasoning capabilities of such AI models.

Content

The class overviews some of the main concepts and developments concerning reasoning in AI, such as Transformers, LLMs, Step-by-Step Reasoning, Tool Use, Planning, Logical Reasoning, Self-Improvement, Generalization on the Unseen or Theorem Proving. 

 

Keywords

Artificial intelligence, foundation models, large language models, reasoning, generalization, logic, proving.

 

Learning Prerequisites

Required courses

Basic machine learning concepts.

 

Learning Outcomes

By the end of the course, the student must be able to:

  • Recognize the basic concepts of AI reasoning and implementing methods in a project.

Resources

Bibliography

List of papers provided when the class starts.

 

Moodle Link

Dans les plans d'études

  • Forme de l'examen: Oral (session libre)
  • Matière examinée: Reasoning in artificial intelligence
  • Cours: 20 Heure(s)
  • Projet: 40 Heure(s)
  • Type: optionnel
  • Forme de l'examen: Oral (session libre)
  • Matière examinée: Reasoning in artificial intelligence
  • Cours: 20 Heure(s)
  • Projet: 40 Heure(s)
  • Type: optionnel

Semaine de référence

Cours connexes

Résultats de graphsearch.epfl.ch.