We investigate the use of self-predicting neural networks for autonomous robot learning within noisy or partially predictable environments. A benchmark experiment is performed in ...
James B. Marshall, Neil K. Makhija, Zachary D. Rot...
We analyze why and how erroneous examples can be beneficially employed in learning mathematics. The `Why' addresses reasoning and attitudes that are rarely fostered in today&...
Constructivism has gained popularity recently, but it is not a completely new learning paradigm. Much of the work within Information Systems Science (IS) and especially within ele...
By learning a range of possible times over which the effect of an action can take place, a robot can reason more effectively about causal and contingent relationships in the world...
A significant portion of the population is at risk of being excluded from online learning environments. People with learning and/or physically disabilities may be prevented from p...