Enhancing Image Classification with Temporally Aware Soft Actor-Critic Algorithms for Real-Time Applications
P. Năvală (TU Delft - Mechanical Engineering)
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)
More Info
expand_more
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.