Abstract
Brains experience sensory information grounded in sensor- relative frames of reference. To compare sensory information from different sensor sources, such as vision and touch, this information needs to be mapped onto each other. To do so, the brain needs to learn suitable spatial transformations and the literature suggests that gain fields accomplish such transformations. However, when transforming three dimensional spaces or even six dimensional configuration spaces then simple gain fields do not scale to such a dimensionality. We are investigating how this curse of dimensionality can be overcome. Based on neural population-encoded, component-wise spatial representations, we show that a hierarchy of gain fields can accomplish higher-dimensional transformations and that its weights can be learned effectively by means of standard backpropagation.
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
Calvert, G.A., Spence, C., Stein, B.E. (eds.): The Handbook of Multisensory Processes. MIT Press, Cambridge (2004)
Holmes, N.P., Spence, C.: The body schema and multisensory representation(s) of peripersonal space. Cognitive Processing 5, 94–105 (2004)
Andersen, R.A., Essick, G.K., Siegel, R.M.: Encoding of spatial location by posterior parietal neurons. Science 230(4724), 456–458 (1985)
Salinas, E., Sejnowski, T.J.: Correlated neuronal activity and the flow of neural information. Nature Reviews Neuroscience 2, 539–550 (2001)
Hwang, E.J., Donchin, O., Smith, M.A., Shadmer, R.: A gain-field encoding of limb position and velocity in the internal model of arm dynamics. PLoS Biology 1, e25 (2003)
Baraduc, P., Guigon, E., Burnod, Y.: Recoding arm position to learn visuomotor transformation. Cerebral Cortex 11, 906–917 (2001)
Chang, S.W.C., Papadimitriou, C., Snyder, L.H.: Using a compound gain field to compute a reach plan. Neuron 64, 744–755 (2009)
Fleischer, F., Christensen, A., Caggiano, V., Thier, P., Giese, M.: Neural theory for the perception of causal actions. Psychological Research 76(4), 476–493 (2012)
Pouget, A., Dyan, T., Zemel, R.: Information processing with population codes. Nature Reviews Neuroscience 1, 125–132 (2000)
Doya, K., Ishii, S., Pouget, A., Rao, R.P.N.: Bayesian brain: Probabilistic approaches to neural coding. The MIT Press (2007)
Ehrenfeld, S., Herbort, O., Butz, M.V.: Modular neuron-based body estimation: Maintaining consistency over different limbs, modalities, and frames of reference. Frontiers in Computational Neuroscience 7(148) (2013)
Maravita, A., Driver, J.: Cross-modal integration and spatial attention in relation to tool use and mirror use: Representing and extending multisensory space near the hand. In: Calvert, G.A., Spence, C., Stein, B.E. (eds.) The Handbook of Multisensory Processes, pp. 819–835. MIT Press, Cambridge (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Kneissler, J., Butz, M.V. (2014). Learning Spatial Transformations Using Structured Gain-Field Networks. In: Wermter, S., et al. Artificial Neural Networks and Machine Learning – ICANN 2014. ICANN 2014. Lecture Notes in Computer Science, vol 8681. Springer, Cham. https://doi.org/10.1007/978-3-319-11179-7_86
Download citation
DOI: https://doi.org/10.1007/978-3-319-11179-7_86
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11178-0
Online ISBN: 978-3-319-11179-7
eBook Packages: Computer ScienceComputer Science (R0)