Francesco Manigrasso

Docente esterno e/o collaboratore didattico
Dipartimento di Automatica e Informatica (DAUIN)

Dottorando in Ingegneria Informatica E Dei Sistemi , 36o cycle (2020-2023)
Dipartimento di Automatica e Informatica (DAUIN)


Dottorato di ricerca

Argomento di ricerca

Robust machine learning models for high dimensional data interpretation


Interessi di ricerca

Machine Learning
Artificial intelligence


The integration of symbolic knowledge representation and learning has the potential to improve traditional deep learning models adding capabilities in terms of inference, reasoning, and representation of high-level concepts. The present research proposal concerns techniques that incorporate deep learning and statistical relational learning (neuro-symbolic models) for the interpretation of multi-dimensional data, such as images.

By allowing the incorporation of prior knowledge in the training process, neuro-symbolic applications can enhance multiple image analysis tasks in various real-life scenarios. The additional possibility to represent the model uncertainty is particularly relevant when coping with limited training data.

Starting from different computer vision tasks like image classification, the research aims at comparing the neural-symbolic architectures with traditional convolutional neural network in terms of accuracy, generalizability, and interpretability.



Corso di laurea magistrale

MostraNascondi A.A. passati

Corso di laurea di 1° livello

  • Informatica. A.A. 2021/22, INGEGNERIA AEROSPAZIALE. Collaboratore del corso
  • Informatica. A.A. 2022/23, INGEGNERIA INFORMATICA. Collaboratore del corso
MostraNascondi A.A. passati


Pubblicazioni più recenti Vedi tutte le pubblicazioni su Porto@Iris