Abstract
Cognition, judgment, action, and expression acquisition have been widely treated in studies on recently developed deep learning. However, although each study has been specialised for specific tasks and goals, cognitive architecture that integrates many different functions remains necessary for the realisation of artificial general intelligence. To that end, a cognitive architecture fully described with restricted Boltzmann machines (RBMs) in a unified way are promising, and we have begun to implement various cognitive functions with an RBM base. In this paper, we propose new stacked half RBMs (SHRBMs) made from layered half RBMs (HRBMs) that handle working memory. We show that an ability to solve maze problems that requires working memory improves drastically when SHRBMs in the agent’s judgment area are used instead of HRBMs or other RBM-based models.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Miri, H.: CernoCAMAL: a probabilistic computational cognitive architecture. Ph.D. thesis, University of Hull (2012)
Laird, J.E.: The Soar Cognitive Architecture. MIT Press, Cambridge (2012)
Anderson, J.R., Lebiere, C.: The newell test for a theory of cognition. Behav. Brain Sci. 26(05), 587–601 (2003)
Goertzel, B.: The Hidden Pattern. Brown Walker, Boca Raton (2006)
Goertzel, B.: Opencog prime: a cognitive synergy based architecture for embodied artificial general intelligence. In: 8th IEEE International Conference on Cognitive Informatics, pp. 60–68 (2009)
Eliasmith, C., Stewart, T.C., Choo, X., Bekolay, T., DeWolf, T., Tang, Y., Rasmussen, D.: A large-scale model of the functioning brain. Science 338(6111), 1202–1205 (2012)
Sutskever, I., Hinton, G.E.: Learning multilevel distributed representations for high-dimensional sequences. In: International Conference on Artificial Intelligence and Statistics (2007)
Yu, Y., Masahiko, O., Masafumi, H.: A learning method for echo state networks using RBM. In: International Symposium on Advanced Intelligent Systems (2015)
Sutskever, I., Hinton, G.E., Taylor, G.W.: The recurrent temporal restricted Boltzmann machine. In: Advances in Neural Information Processing Systems (2009)
Boulanger-Lewandowski, N., Bengio, Y., Vincent, P.: Modeling temporal dependencies in high-dimensional sequences: application to polyphonic music generation and transcription. In: Proceedings of the 29th International Conference on Machine Learning (2012)
Osawa, M., Hagiwara, M.: A proposal of novel data detection method and its application to incremental learning for RBMs. IEICE Technical report, ME and Bio Cybernetics, vol. 114, no. 259, pp 283–288 (2015). (In Japanese)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Osawa, M., Yamakawa, H., Imai, M. (2016). An Implementation of Working Memory Using Stacked Half Restricted Boltzmann Machine. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science(), vol 9947. Springer, Cham. https://doi.org/10.1007/978-3-319-46687-3_38
Download citation
DOI: https://doi.org/10.1007/978-3-319-46687-3_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46686-6
Online ISBN: 978-3-319-46687-3
eBook Packages: Computer ScienceComputer Science (R0)