Study of the integration of stochastic analysis tools with Machine Learning models in the training and operation of Large Language Models (LLM).

Starting date
February 7, 2024
Duration (months)
11
Departments
Computer Science
Managers or local contacts
Di Persio Luca

Large Language Models (LLM) are machine learning models, based on neural network architectures, and developed in order to process large masses of data to understand, generate and translate text similar to the human one. The aim of the project is to use stochastic analysis tools to optimize the training and control phases of LLM models also in relation to their transparency and interpretability characteristics.

Sponsors:

HPA s.r.l.
Funds: assigned and managed by the department

Project participants

Luca Di Persio
Associate Professor
Research areas involved in the project
Metodi e modelli matematici
Stochastic analysis

Activities

Research facilities

Share