Enhancing Image Classification with Temporally Aware Soft Actor-Critic Algorithms for Real-Time Applications

Master Thesis (2024)
Author(s)

P. Năvală (TU Delft - Mechanical Engineering)

Contributor(s)

Michel Verhaegen – Mentor (TU Delft - Team Michel Verhaegen)

Oleg Soloviev – Mentor (TU Delft - Team Michel Verhaegen)

Aleksandr Dekhovich – Mentor (TU Delft - Team Michel Verhaegen)

Nitin Myers – Graduation committee member (TU Delft - Team Nitin Myers)

Faculty
Mechanical Engineering
More Info
expand_more
Publication Year
2024
Language
English
Graduation Date
29-08-2024
Awarding Institution
Delft University of Technology
Programme
['Mechanical Engineering | Systems and Control']
Faculty
Mechanical Engineering
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.

Abstract

The thesis presents a novel approach to optimizing input computation for minimizing classification error in image classification tasks. It leverages the capabilities of the Soft Actor-Critic (SAC) algorithm, a reinforcement learning method tailored for continuous action spaces. The focus is on developing a real-time adaptable feedback loop that continuously learns and adjusts inputs based on classifier output probabilities. Key to this approach is the incorporation of a Gated Recurrent Unit (GRU) architecture within the SAC framework to capture temporal dependencies, addressing the challenge of ever-increasing state dimensions.

Files

License info not available