REAL

Strategic data navigation : information value-based sample selection

Balogh, Csanád Levente and Pelenczei, Bálint and Kővári, Bálint and Bécsi, Tamás (2024) Strategic data navigation : information value-based sample selection. ARTIFICIAL INTELLIGENCE REVIEW, 57 (7). No. 187. ISSN 0269-2821

[img]
Preview
Text
s10462-024-10813-3.pdf - Published Version
Available under License Creative Commons Attribution.

Download (2MB) | Preview

Abstract

Artificial Intelligence represents a rapidly expanding domain, with several industrial applications demonstrating its superiority over traditional techniques. Despite numerous advancements within the subfield of Machine Learning, it encounters persistent challenges, highlighting the importance of ongoing research efforts. Among its primary branches, this study delves into two categories, being Supervised and Reinforcement Learning, particularly addressing the common issue of data selection for training. The inherent variability in informational content among data points is apparent, wherein certain samples offer more valuable information to the neural network than others. However, evaluating the significance of various data points remains a non-trivial task, generating the need for a robust method to effectively prioritize samples. Drawing inspiration from Reinforcement Learning principles, this paper introduces a novel sample prioritization approach, applied to Supervised Learning scenarios, aimed at enhancing classification accuracy through strategic data navigation, while exploring the boundary between Reinforcement and Supervised Learning techniques. We provide a comprehensive description of our methodology while revealing the identification of an optimal prioritization balance and demonstrating its beneficial impact on model performance. Although classification accuracy serves as the primary validation metric, the concept of information density-based prioritization encompasses wider applicability. Additionally, the paper investigates parallels and distinctions between Reinforcement and Supervised Learning methods, declaring that the foundational principle is equally relevant, hence completely adaptable to Supervised Learning with appropriate adjustments due to different learning frameworks. The project page and source code are available at: https://csanadlb.github.io/sl_prioritized_sampling/ .

Item Type: Article
Uncontrolled Keywords: Supervised learning · Classifcation · Sampling efciency · Sample prioritization · Reinforcement learning
Subjects: Q Science / természettudomány > QA Mathematics / matematika > QA75 Electronic computers. Computer science / számítástechnika, számítógéptudomány
SWORD Depositor: MTMT SWORD
Depositing User: MTMT SWORD
Date Deposited: 24 Sep 2024 13:50
Last Modified: 24 Sep 2024 13:50
URI: https://real.mtak.hu/id/eprint/205717

Actions (login required)

Edit Item Edit Item