None

Bachelor thesis (2021)

Authors

S. Şen Electrical Engineering, Mathematics and Computer Science

Contributors

J.W. Böhmer Algorithmics - EEMCS (supervisor 1)
Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright: © 2021 Sina Şen
More Info
expand_more

Published Date

02-07-2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

The introduction of Attention Long Short Term Memory (ALSTM) produces an alternative to Long Short Term Memory (LSTM) by aiming to optimize information passing via removing the complexity of the cells in LSTM. In this work, the results and comparison of the performance of LSTM algorithms versus ALSTM architectures are assessed through the forecast of airline passenger numbers over months. The results are analyzed through qualitative and quantitative data. The hypothesis made in this paper is that ALSTM will perform better than the LSTM, and the results show that the hypothesis was correct under some circumstances, although by a small margin.