ε-mdps: learning in varying environments
The Journal of Machine Learning Research
Automatic feature localisation with constrained local models
Pattern Recognition
The many faces of optimism: a unifying approach
Proceedings of the 25th international conference on Machine learning
Optimistic initialization and greediness lead to polynomial time learning in factored MDPs
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Identification of Recurrent Neural Networks by Bayesian Interrogation Techniques
The Journal of Machine Learning Research
Deformable Model Fitting by Regularized Landmark Mean-Shift
International Journal of Computer Vision
Hi-index | 0.00 |
AGI could manifest itself in human-computer interactions. However, the computer should know what is on the mind of the user, since reinforcement learning, the main building block of AGI, is severely spoiled for partially observed states. Technological advances offer tools to uncover some of these hidden components of the 'state'. Here, for the first time, we apply an AGI architecture for the optimization of human performance. In particular, we measure facial parameters and optimize users' writing speed working with head motion controlled writing tool. We elaborate on how to extend this optimization scheme to more complex scenarios.