Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/248137
Title: | PRINCIPLED LEARNING | Authors: | THEIVENDIRAM PRANAVAN | ORCID iD: | ![]() |
Keywords: | PRINCIPLED LEARNING, MACHINE LEARNING, DELAYED FEEDBACK, MULTI-TASK LEARNING, PREDICTIVE CODING, CONTINUAL LEARNING | Issue Date: | 18-Sep-2023 | Citation: | THEIVENDIRAM PRANAVAN (2023-09-18). PRINCIPLED LEARNING. ScholarBank@NUS Repository. | Abstract: | The thesis explores leveraging principles from human learning to enhance machine learning models. It delves into four key principles: continual learning, recency, similarity-based learning, and predictive coding. The first part introduces a continual learning method, in which an Agent learns continuously over time, accommodating delayed feedback. This strategy enables flexibility in learning and improves performance in tasks like image classification and captioning. The second part focuses on using task similarity to enhance multi-task learning. We experiment with how virtual tasks are helpful in improving the performance of real tasks. The third part introduces a method for anomaly detection in multi-variate time series data. By leveraging predictive coding, it effectively models temporal dependencies and correlations, outperforming existing anomaly detection methods. Lastly, continual learning is demonstrated beneficial in medical imaging, aiding in data security by facilitating model sharing across multiple sources with confidentiality constraints. | URI: | https://scholarbank.nus.edu.sg/handle/10635/248137 |
Appears in Collections: | Ph.D Theses (Open) |
Show full item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
PranavanT.pdf | 12.94 MB | Adobe PDF | OPEN | None | View/Download |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.