A typical goal for transfer learning algorithms is to utilize knowledge gained in a source task to learn a target task faster. Recently introduced transfer methods in reinforcemen...
— Context is critical for reducing the uncertainty in object detection. However, context modelling is challenging because there are often many different types of contextual infor...
In many graph-based semi-supervised learning algorithms, edge weights are assumed to be fixed and determined by the data points' (often symmetric) relationships in input space...
This paper proposes and develops a new graph-based semi-supervised learning method. Different from previous graph-based methods that are based on discriminative models, our method...
Extract-Transform-Load (ETL) workflows are data centric workflows responsible for transferring, cleaning, and loading data from their respective sources to the warehouse. Previous ...