Výsledky vyhledávání - "Singh, Pranshu"

Report

Knowledge Capture and Replay for Continual Learning

Autor: Gopalakrishnan, Saisubramaniam, Singh, Pranshu Ranjan, Fayek, Haytham, Ramasamy, Savitha, Ambikapathi, Arulmurugan

Deep neural networks have shown promise in several domains, and the learned data (task) specific information is implicitly stored in the network parameters. Extraction and utilization of encoded knowledge representations are vital when data is no lon

Externí odkaz: http://arxiv.org/abs/2012.06789

Zobrazit plný text záznamu

Report

Semi-supervised and Unsupervised Methods for Heart Sounds Classification in Restricted Data Environments

Autor: Unnikrishnan, Balagopal, Singh, Pranshu Ranjan, Yang, Xulei, Chua, Matthew Chin Heng

Automated heart sounds classification is a much-required diagnostic tool in the view of increasing incidences of heart related diseases worldwide. In this study, we conduct a comprehensive study of heart sounds classification by using various supervi

Externí odkaz: http://arxiv.org/abs/2006.02610

Zobrazit plný text záznamu

Report

Classify and Generate: Using Classification Latent Space Representations for Image Generations

Autor: Gopalakrishnan, Saisubramaniam, Singh, Pranshu Ranjan, Yazici, Yasin, Foo, Chuan-Sheng, Chandrasekhar, Vijay, Ambikapathi, ArulMurugan

Publikováno v: Saisubramaniam Gopalakrishnan, Pranshu Ranjan Singh et. al., Classify and generate: Using classification latent space representations for image generations, Neurocomputing, Volume 471, 2022, Pages 296-334, ISSN 0925-2312

Utilization of classification latent space information for downstream reconstruction and generation is an intriguing and a relatively unexplored area. In general, discriminative representations are rich in class-specific features but are too sparse f

Externí odkaz: http://arxiv.org/abs/2004.07543

Zobrazit plný text záznamu