COMPARATIVE STUDY OF SURROGATE TECHNIQUES FOR HYPERPARAMETER OPTIMIZATION IN RECURRENT NEURAL NETWORK

HILMI, MUHAMMAD ZAHID (2023) COMPARATIVE STUDY OF SURROGATE TECHNIQUES FOR HYPERPARAMETER OPTIMIZATION IN RECURRENT NEURAL NETWORK. Masters thesis, Universiti Teknologi PETRONAS.

[thumbnail of 2023_PhD in IT_thesis submission_1900298_Muhammad Zahid bin Hilmi.pdf] Text
2023_PhD in IT_thesis submission_1900298_Muhammad Zahid bin Hilmi.pdf
Restricted to Registered users only

Download (1MB)

Abstract

Long Short-Term Memory (LSTM) models are a type of recurrent neural network (RNN) well-suited for tasks requiring the model to remember long-term dependencies. This makes them a promising approach for ET rate estimation, as ET is a process that is influenced by various factors that may occur over long periods.

Item Type: Thesis (Masters)
Subjects: T Technology > T Technology (General)
Departments / MOR / COE: Engineering > Information Technology
Depositing User: Mr Ahmad Suhairi Mohamed Lazim
Date Deposited: 14 Sep 2023 07:11
Last Modified: 14 Sep 2023 07:11
URI: http://utpedia.utp.edu.my/id/eprint/24854

Actions (login required)

View Item
View Item