A Top-Down Approach for a Synthetic Autobiographical Memory System
Autobiographical memory (AM) refers to the organisation of one’s experience into a coherent narrative. The exact neural mechanisms responsible for the manifestation of AM in humans are unknown. On the other hand, the field of psychology has provided us with useful understanding about the functionality of a bio-inspired synthetic AM (SAM) system, in a higher level of description. This paper is concerned with a top-down approach to SAM, where known components and organisation guide the architecture but the unknown details of each module are abstracted. By using Bayesian latent variable models we obtain a transparent SAM system with which we can interact in a structured way. This allows us to reveal the properties of specific sub-modules and map them to functionality observed in biological systems. The top-down approach can cope well with the high performance requirements of a bio-inspired cognitive system. This is demonstrated in experiments using faces data.
KeywordsSynthetic autobiographical memory Hippocampus Robotics Deep Gaussian process MRD
Unable to display preview. Download preview PDF.
- 1.Damianou, A., Lawrence, N.: Deep Gaussian processes. Proceedings of the 16th International Workshop on A.I. and Statistics (AISTATS), pp. 207–215 (2013)Google Scholar
- 2.Evans, M.H., Fox, C.W., Prescott, T.J.: Machines learning - towards a new synthetic autobiographical memory. In: Duff, A., Lepora, N.F., Mura, A., Prescott, T.J., Verschure, P.F.M.J. (eds.) Living Machines 2014. LNCS, vol. 8608, pp. 84–96. Springer, Heidelberg (2014) Google Scholar
- 4.Rojas, R.: Neural networks: a systematic introduction. Springer Science & Business Media (1996)Google Scholar
- 7.Bengio, Y., LeCun, Y.: Tutorial on Learning Deep Architectures. Videlectures.net, June 2009. http://videolectures.net/icml09_bengio_lecun_tldar/
- 8.Nielsen, M. A.: Neural Networks and Deep Learning. Determination Press (2015)Google Scholar
- 9.Bishop, C. M.: Pattern Recognition and Machine Learning. Springer-Verlag (2006). ISBN 0387310738Google Scholar
- 10.Damianou, A., Ek, C.H., Titsias, M., Lawrence, N.: Manifold relevance determination. Proceedings of the 29th International Conference on Machine Learning (ICML), pp. 145–152. omnipress, New York (2012)Google Scholar
- 14.Damianou, A., Titsias, M., Lawrence, N.: Variational inference for uncertainty on the inputs of Gaussian process models. arXiv preprint, arXiv:1409.2287 (2014)
- 15.Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Mach. Intelligence 23(6) (2001)Google Scholar
- 17.Luvizotto, A., Renn-Costa, C., Verschure, P.: A Framework for Mobile Robot Navigation Using a Temporal Population Code. Biomimetic & Biohybrid Systems (2012)Google Scholar