Explaining Features of LSTM Model Learned on Human Motion Data – Bc. Tomáš Jevočin
Bc. Tomáš Jevočin
Master's thesis
Explaining Features of LSTM Model Learned on Human Motion Data
Explaining Features of LSTM Model Learned on Human Motion Data
Abstract:
Cieľom práce je vysvetliť, aké features sa model neurónovej siete LSTM naučil na základe údajov o kostre ľudského pohybu. Na získanie usporiadania dôležitosti deep features aplikujeme DeepSHAP. Následne použijeme LRP upravené pre architektúru LSTM na získanie vstupného mapovania relevancie pre ľubovoľný fixný feature, ktorý môžeme vizualizovať. Získané usporiadania funkcií potom vyhodnotíme pomocou …moreAbstract:
The thesis aims to explain what features an LSTM neural network model learned on top of human motion skeleton data. We apply DeepSHAP to obtain deep feature importance ordering. We then use LRP adjusted for LSTM architecture to acquire input relevance mapping for any fixed feature, which we can visualize. We then evaluate the obtained feature orderings with the help of a 1-NN model trained and evaluated …more
Language used: English
Date on which the thesis was submitted / produced: 15. 12. 2023
Identifier:
https://is.muni.cz/th/fl7nv/
Thesis defence
- Date of defence: 8. 2. 2024
- Supervisor: doc. RNDr. Jan Sedmidubský, Ph.D.
- Reader: prof. Ing. Pavel Zezula, CSc.
Citation record
Full text of thesis
Contents of on-line thesis archive
Published in Theses:- světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatikyMasaryk University
Faculty of InformaticsMaster programme / field:
Artificial intelligence and data processing / Big data