Context-sensitive Multiple Task Learning, or csMTL, is presented as a method of inductive transfer that uses a single output neural network and additional contextual inputs for learning multiple tasks. The csMTL method is tested on three task domains and shown to produce hypotheses for a primary task that are significantly better than standard MTL… (More)
Multiple task learning (MTL) neural networks are one of the better documented methods of inductive transfer of task knowledge (Caruana 1997). An MTL network is a feed-forward multi-layer network with an output node for each task being learned. The standard back-propagation of error learning algorithm is used to train all tasks in parallel. The sharing of… (More)
A significant advance in inductive modelling are systems that retain learned knowledge and selectively transfer portions of that knowledge as a source of inductive bias. We define such to be machine lifelong learning (ML3) systems. This paper makes an initial effort at specifying the scope of ML3 systems and their functional requirements.