Abstract. This work extends studies of Angluin, Lange and Zeugmann on the dependence of learning on the hypotheses space chosen for the class. In subsequent investigations, uniform...
In transfer learning the aim is to solve new learning tasks using fewer examples by using information gained from solving related tasks. Existing transfer learning methods have be...
The recent Predictive Linear Gaussian model (or PLG) improves upon traditional linear dynamical system models by using a predictive representation of state, which makes consistent...
Rademacher and Gaussian complexities are successfully used in learning theory for measuring the capacity of the class of functions to be learned. One of the most important propert...
Deficiencies in the ability to map letters to sounds are currently considered to be the most likely early signs of dyslexia [4]. This has motivated the use of Literate, a compute...
Mikko Vilenius, Janne V. Kujala, Ulla Richardson, ...