Abstract
We present ways of defining neuromanifolds – models of stochastic matrices – that are compatible with the maximization of an objective function such as the expected reward in reinforcement learning theory. Our approach is based on information geometry and aims to reduce the number of model parameters with the hope to improve gradient learning processes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
S. Amari. Natural Gradient Works Efficiently in Learning. Neural Comput., 10(2) (1998) 251–276.
S. Amari, K. Kurata, H. Nagaoka. Information Geometry of Boltzmann machines. IEEE T. Neural Networks, 3(2) (1992) 260–271.
N. Ay, T. Wennekers. Dynamical Properties of Strongly Interacting Markov Chains. Neural Networks 16 (2003) 1483–1497.
G. Lebanon. Axiomatic geometry of conditional models. IEEE Transactions on Information Theory, 51(4) (2005) 1283–1294.
G. Montúfar, N. Ay. Refinements of Universal Approximation Results for DBNs and RBMs. Neural Comput. 23(5) (2011) 1306–1319.
R. Sutton, A. Barto. Reinforcement Learning. MIT Press (1998).
R. Sutton, D. McAllester, S. Singh, Y. Mansour. Policy Gradient Methods for Reinforcement Learning with Function Approximation. Adv. in NIPS 12 (2000) 1057–1063.
K.G. Zahedi, N. Ay, R. Der. Higher Coordination With Less Control – A Result of Information Maximization in the Sensorimotor Loop. Adaptive Behavior 18 (3–4) (2010), 338–355.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media Dordrecht
About this paper
Cite this paper
Ay, N., Montúfar, G., Rauh, J. (2013). Selection Criteria for Neuromanifolds of Stochastic Dynamics. In: Yamaguchi, Y. (eds) Advances in Cognitive Neurodynamics (III). Springer, Dordrecht. https://doi.org/10.1007/978-94-007-4792-0_20
Download citation
DOI: https://doi.org/10.1007/978-94-007-4792-0_20
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-007-4791-3
Online ISBN: 978-94-007-4792-0
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)