Sort by
Refine Your Search
-
models (eg auto-encoders and generative adversarial networks) and reinforcement/imitation learning algorithms for Markov Decision Processes. The application areas are different problems in text processing
-
representations complicate transparency and compliance checks with data protection and privacy legislation (e.g., GDPR) whether performed by humans or computer systems. Second, both privacy-preserving distributed
-
. Wallace ", Computer Journal , Vol. 51, No. 5 (Sept. 2008) [Christopher Stewart WALLACE (1933-2004) memorial special issue [and front cover and back cover ]], pp 523-560 (and here ). www.doi .org
-
support conversation can be well combined with the desired emotion and voice patterns for generating natural and empathetic speech. However, current deep generative models perform poorly for compositional
-
presents challenges to research in advancing technological solutions dealing with this data. This project will research improvements to classification models as well as ways in which AI techniques
-
Skip to main content Main Menu - Primary Home Projects Supervisors Expression of Interest Contact Computational drug discovery Primary supervisor Geoff Webb Research area Data Science and Artificial
-
techniques for annotation, active learning (based on either deep learning or Bayesian learning), semi-supervised learning, transfer learning, imitation learning, etc., aiming to ensure the data and models
-
initiate an application, all in one place. Browse Research projects Honours and Masters project Supervisors Login Recently added Development of a GIS-Based Model for Active Citizenry Street-Level Environment
-
addition to audio. Candidates will be expected to devise novel multi-modal generation models by incorporating ideas and techniques from various techniques, such as causality, deep learning, deep reinforcement