Nov. 14, 2023, 7:54 p.m. |

News on Artificial Intelligence and Machine Learning

Unsupervised domain adaptation has garnered a great amount of attention and research in past decades. Among all the deep-based methods, the autoencoder-based approach has achieved sound performance for its fast convergence speed and a no-label requirement. The existing methods of autoencoders just serially connect the features generated by different autoencoders, which poses challenges for discriminative representation learning and which fails to find the real cross-domain features.

attention autoencoder autoencoders computer sciences convergence domain domain adaptation features generated performance research sound speed unsupervised

Lecturer in Social Data Analytics

@ The University of Hong Kong | Hong Kong

Junior Data Scientist

@ Valerann | London, England, United Kingdom

Senior Data Lead architect (REF2159Z)

@ Deutsche Telekom IT Solutions | Budapest, Hungary

Senior Specialist - Data Management

@ Marsh McLennan | Norwich - Willow

Data Engineer – AI Applications

@ HP | TW2WA - Teleworker/Offsite-USA-WA

Senior Data Quality and Governance Analyst

@ JLL | IND-CORP Bengaluru-TDIM - PTT