Mishra, S and Sundaram, S (2023) A Memory-Free Evolving Bipolar Neural Network for Efficient Multi-Label Stream Learning. In: UNSPECIFIED.
PDF
Ica_iee_int_con_aco_spe_sig_pro_pro_2023.pdf - Published Version Restricted to Registered users only Download (961kB) | Request a copy |
Abstract
Many fields, like document tagging, video labeling, and medical analysis, require associating the samples with multiple non-exclusive labels, driving the research in multi-label learning. Unlike several multi-label learning setups, practical applications are challenging because they need learning from a stream of samples and labels. This work proposes an Evolving Bipolar Network architecture called EBN-MSL consisting of two parallel layers trained in a maximum margin framework to learn efficiently in a continual multi-label learning scenario without utilizing any samples stored from previous tasks. This work considers two learning setups, one for separately learning each task (SEA�) and another for jointly learning subsequent tasks (SEA). Experiments on benchmark multi-label learning datasets establish the superior learning capability of EBN-MSL in the presence of samples having all positive or negative labels. Results indicate that EBN-MSL (both SEA and SEA� setups) significantly outperforms the current state-of-the-art architecture-based continual multi-label learning algorithm. © 2023 IEEE.
Item Type: | Conference Paper |
---|---|
Publication: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
Publisher: | Institute of Electrical and Electronics Engineers Inc. |
Additional Information: | The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc. |
Department/Centre: | Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering) |
Date Deposited: | 04 Mar 2024 07:53 |
Last Modified: | 04 Mar 2024 07:53 |
URI: | https://eprints.iisc.ac.in/id/eprint/84279 |
Actions (login required)
View Item |