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

Master thesis (2024)

Authors

P. Năvală Mechanical Engineering

Contributors

M.H.G. Verhaegen Team Michel Verhaegen - Mechanical, Maritime and Materials Engineering (mentor)
O.A. Soloviev Team Michel Verhaegen - Mechanical, Maritime and Materials Engineering (mentor)
A. Dekhovich Team Michel Verhaegen - Mechanical, Maritime and Materials Engineering (mentor)
N.J. Myers Team Nitin Myers - Mechanical, Maritime and Materials Engineering (graduation committee member)
Faculty
Mechanical Engineering
More Info
expand_more

Published Date

29-08-2024

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

Mechanical Engineering

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.