Selection Criteria for Neuromanifolds of Stochastic Dynamics
Nihat Ay, Guido Montúfar, and Johannes Rauh
Contact the author: Please use for correspondence this email.
Submission date: 19. Apr. 2011
published in: Advances in cognitive neurodynamics III : proceedings of the 3rd International Conference on Cognitive Neurodynamics 2011 ; [June 9-13, 2011, Hilton Niseko Village, Hokkaido, Japan] / Y. Yamaguchi (ed.)
Dordrecht : Springer, 2013. - P. 147 - 154
(Advances in cognitive neurodynamics)
DOI number (of the published article): 10.1007/978-94-007-4792-0_20
MSC-Numbers: 62B10, 82C32
Keywords and phrases: learning, neural nets, information geometry
Download full preprint: PDF (2108 kB)
We present ways of deﬁning neuromanifolds – models of stochastic matrices – that are compatible with the maximization of an objective function (reward in reinforcement learning, predictive information in robotics, information ﬂow in neural networks). Our approach is based on information geometry and aims at the reduction of model parameters with the hope to improve gradient learning processes. We discuss advantages and shortcomings of this approach.