Amb motiu del tancament d'estiu, la validació de documents es reprendrà a partir del 28 d'agost de 2026. Disculpeu les molèsties.
Con motivo del cierre de verano, la validación de documentos se reanudará a partir del 28 de agosto de 2026. Disculpad las molestias
Due to the summer closure, document validation will resume starting August 28, 2026. We apologize for any inconvenience.

Files

Exploring-the-Emergence-of-Temperature-Concept-within-Deep-Neural-Networks-main.zip (1.56 MB)
tfm_gallego_racero_dario.pdf (1.44 MB)

Document type

Master thesis

Publication date

2023-06-30

Publication license

cc-by-nc-nd (c) Dario Gallego Racero, 2023
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/213405

Exploring the emergence of temperature concept within deep neural networks through next-frame image prediction

Journal Title

Authors

Director/Tutor

Journal ISSN

Volume Title

Related resource

Abstract

Deep learning has revolutionized numerous domains by enabling the creation of powerful models capable of learning complex patterns from vast amounts of data. However, the intrinsic opacity of deep neural networks has raised concerns about their decision-making processes, limiting their application in critical domains such as healthcare, finance and justice. The study of explainability in deep learning models aims to shed light on the inner workings of these models, enabling us to understand how they arrive at their predictions and uncovering emergent concepts that are not explicitly present in the training data. A study of the emergence of the concept of temperature was performed by forcing a reconstruction and prediction of the next frame in images of physical systems of balls with movement. The goal was to determine whether the neural network could acquire an understanding of temperature. Experimental observations were performed with architectures such as Convolutional Autoencoders and U-Net, but the neural networks did not accomplish the task of learning the temperature concept due to many needed concepts that were not considered initially. Despite that, a prediction of the temperature value was performed by using the optical flow of the system.

Description

Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Curs: 2022-2023. Tutor: Oriol Pujol Vila i Jordi Vitrià i Marca

Subject

Aprenentatge automàtic, Xarxes neuronals convolucionals, Temperatura, Treballs de fi de màster

Subject (English)

Machine learning, Convolutional neural networks, Temperature, Master's thesis

Citation

Collections

Màster Oficial - Fonaments de la Ciència de Dades
Programari - Treballs de l'alumnat

Citation

GALLEGO RACERO, Dario. Exploring the emergence of temperature concept within deep neural networks through next-frame image prediction. [consulted: 7 of August of 2026]. Available at: https://hdl.handle.net/2445/213405

Export metadata

JSON - METS

Share record