Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Berman, J., Bruckman, A.: The Turing game: Exploring identity in an online environment. Convergence 7, 83–102 (2001)
Cristinacce, D., Cootes, T.: Automatic feature localisationwith constrained localmodel. Pattern Rec. 41, 3054–3067 (2008)
Even-Dar, E., Mansour, Y.: Convergence of optimistic and incremental Q-learning. In: Advances in Neural Information Processing Systems, vol. 14, pp. 1499–1506 (2001)
Khalil, H.K.: Nonlinear Systems. Prentice Hall, NJ (2002)
Loebner, H.: How to hold a Turing test contest. In: Parsing the Turing Test, pp. 173–179. Springer, Netherlands (2009)
Lőrincz, A.: Learning and representation: From compressive sampling to the ‘symbol learning problem’. In: Handbook of Large-Scale Random Networks, pp. 445–488. Springer, Heidelberg (2009)
Lőrincz, A., Bárdosi, Z., Takács, D.: Sketch of an AGI architecture with illustration. In: 3rd Conf. on Artif. Gen. Intel. (2010), http://dx.doi.org/10.2991/agi.2010.40
Póczos, B., Lőrincz, A.: Identification of recurrent neural networks by Bayesian interrogation techniques. J. of Mach. Learn. Res. 10, 515–554 (2009)
Saragih, J., Lucey, S., Cohn, J.: Deformable model fitting by regularized landmark mean-shifts. Int. J. Comp. Vision (in press)
Schaul, T., Togelius, J., Schmidhuber, J.: Measuring intelligence through game. J. Artif. Gen. Intell. 2, 1–19 (2010)
Szita, I., Lőrincz, A.: The many faces of optimism: A unifying approach. In: 25th Int. Conf. on Mach. Learn., pp. 1048–1055. Omnipress (2008)
Szita, I., Lőrincz, A.: Optimistic initialization and greediness lead to polynomial time learning in factored MDPs. In: 26th Int. Conf. on Mach. Learn., pp. 126–133. Omnipress (2009)
Szita, I., Takács, B., Lőrincz, A.: Epsilon-MDPs: Learning in varying environments. J. Mach. Learn. Res. 3, 145–174 (2003)
Ward, D.J., MacKay, D.J.C.: Fast hands-free writing by gaze direction. Nature 418, 838 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lőrincz, A., Takács, D. (2011). AGI Architecture Measures Human Parameters and Optimizes Human Performance. In: Schmidhuber, J., Thórisson, K.R., Looks, M. (eds) Artificial General Intelligence. AGI 2011. Lecture Notes in Computer Science(), vol 6830. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22887-2_37
Download citation
DOI: https://doi.org/10.1007/978-3-642-22887-2_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22886-5
Online ISBN: 978-3-642-22887-2
eBook Packages: Computer ScienceComputer Science (R0)