ICANN 2007: Artificial Neural Networks – ICANN 2007 pp 129-138 | Cite as
Learning Temporally Stable Representations from Natural Sounds: Temporal Stability as a General Objective Underlying Sensory Processing
Conference paper
Abstract
In order to understand the general principles along which sensory processing is organized, several recent studies optimized particular coding objectives on natural inputs for different modalities. The homogeneity of neocortex indicates that a sensitive objective should be able to explain response properties of different sensory modalities. The temporal stability objective was successfully applied to somatosensory and visual processing. We investigate if this objective can also be applied to auditory processing and serves as a general optimization objective for sensory processing. In case of audition, this translates to a set of non-linear complex filters optimized for temporal stability on natural sounds. We show that following this approach we can develop filters that are localized in frequency and time and extract the frequency content of the sound wave. A subset of these filters respond invariant to the phase of the sound. A comparison of the tuning of these filters to the tuning of cat auditory nerves shows a close match. This suggests that temporal stability can be seen as a general objective describing somatosensory, visual and auditory processing.
Keywords
Center Frequency Auditory Nerve Sensory Processing Natural Image Auditory Processing
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
- 1.Sur, M., Rubenstein, J.L.R.: Patterning and plasticity of the cerebral cortex. Science 310(5749), 805–810 (2005)CrossRefGoogle Scholar
- 2.Horng, S.H., Sur, M.: Visual activity and cortical rewiring: activity-dependent plasticity of cortical networks. Prog. Brain Res. 157, 3–11 (2006)CrossRefGoogle Scholar
- 3.Douglas, R., Martin, K.: Neocortex. In: Shepherd, G. (ed.) The Synaptic Organization of the Brain, pp. 459–509. Oxford University Press, New York (1998)Google Scholar
- 4.Simoncelli, E.P., Olshausen, B.A.: Natural image statistics and neural representation. Annu. Rev. Neurosci 24, 1193–1216 (2001)CrossRefGoogle Scholar
- 5.Olshausen, B., Field, D.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. NatureEmergence of simple-cell receptive field properties by learning a sparse code for natural images 381(6583), 607–609 (1996)Google Scholar
- 6.Hoyer, P.O., Hyvärinen, A.: A multi-layer sparse coding network learns contour coding from natural images. Vision Res. 42(12), 1593–1605 (2002)CrossRefGoogle Scholar
- 7.Hurri, J., Hyvärinen, A.: Simple-cell-like receptive fields maximize temporal coherence in natural video. Neural Comput 15(3), 663–691 (2003)MATHCrossRefGoogle Scholar
- 8.Berkes, P., Wiskott, L.: Slow feature analysis yields a rich repertoire of complex cell properties. J. Vis. 5(6), 579–602 (2005)CrossRefGoogle Scholar
- 9.Körding, K.P., Kayser, C., Einhäuser, W., König, P.: How are complex cell properties adapted to the statistics of natural stimuli? J. Neurophysiol 91(1), 206–212 (2004)CrossRefGoogle Scholar
- 10.Hashimoto, W.: Quadratic forms in natural images. Network 14(4), 765–788 (2003)CrossRefGoogle Scholar
- 11.Einhäuser, W., Kayser, C., König, P., Körding, K.P.: Learning the invariance properties of complex cells from their responses to natural stimuli. Eur. J. Neurosci. 15(3), 475–486 (2002)CrossRefGoogle Scholar
- 12.Kayser, C., Einhäuser, W., Dümmer., O., König, P., Körding, K.P.: Extracting slow subspaces from natural videos leads to complex cells. In: Dorffner, G., Bischof, H., Hornik, K. (eds.) ICANN 2001. LNCS, vol. 2130, pp. 1075–1080. Springer, Heidelberg (2001)CrossRefGoogle Scholar
- 13.Einhäuser, W., Kayser, C., Körding, K., König, P.: Learning distinct and complementary feature-selectivities from natural colour videos. Journal of NeuroscienceLearning distinct and complementary feature-selectivities from natural colour videos 21, 43–52 (2003)Google Scholar
- 14.Stringer, S.M., Rolls, E.T.: Invariant object recognition in the visual system with novel views of 3D objects. Neural Comput. 14(11), 2585–2596 (2002)MATHCrossRefGoogle Scholar
- 15.Einhäuser, W., Hipp, J., Eggert, J., Körner, E., König, P.: Learning viewpoint invariant object representations using a temporal coherence principle. Biol. Cybern 93(1), 79–90 (2005)MATHCrossRefGoogle Scholar
- 16.Wyss, R., König, P., Verschure, P.F.M.J.: A Model of the Ventral Visual System Based on Temporal Stability and Local Memory. PLoS Biol. 4(5), e120 (2006)CrossRefGoogle Scholar
- 17.Riesenhuber, R., Poggio, T.: Hierarchical models of object recognition in cortex. Nature Neuroscience 2, 1019–1025 (1999)CrossRefGoogle Scholar
- 18.König, P., Krüger, N.: Symbols as Self-emergent Entities in an Optimization Process of Feature Extraction and Predictions. Biol. Cybern 94(4), 325–334 (2006)MATHCrossRefGoogle Scholar
- 19.Lewicki, M.S.: Efficient coding of natural sounds. Nat. Neurosci 5(4), 356–363 (2002)CrossRefGoogle Scholar
- 20.Smith, E., Lewicki, M.S.: Efficient coding of time-relative structure using spikes. Neural. Comput. 17(1), 19–45 (2005)MATHCrossRefGoogle Scholar
- 21.Smith, E.C., Lewicki, M.S.: Efficient auditory coding. Nature 439(7079), 978–982 (2006)CrossRefGoogle Scholar
- 22.Klein, D., König, P., Körding, K.: Sparse spectrotemporal coding of sounds. Eurasip JaspSparse spectrotemporal coding of sounds 3, 659–667 (2003)Google Scholar
- 23.Hipp, J., Einhäuser, W., Conradt, J., König, P.: Learning of somatosensory representations for texture discrimination using a temporal coherence principle. Network 16(2-3), 223–238 (2005)Google Scholar
- 24.Shamma, S.: On the role of space and time in auditory processing. Trends Cogn. Sci. 5(8), 340–348 (2001)CrossRefGoogle Scholar
- 25.Sur, M., Leamey, C.A.: Development and plasticity of cortical areas and networks. Nature Reviews Neuroscience 2, 251–262 (2001)CrossRefGoogle Scholar
- 26.Dennis, D., O’Leary, M.: Do cortical areas emerge from a protocortex? Trends in Neuroscience 12(10), 400–406 (1989)CrossRefGoogle Scholar
- 27.Sur, M., Garraghty, P., Roe, A.: Experimentally induced visual projections into auditory thalamus and cortex. Science 242, 1437–1441 (1988)CrossRefGoogle Scholar
- 28.Rhode, W.S., Smith, P.H.: Characteristics of tone-pip response patterns in relationship to spontaneous rate in cat auditory nerve fibers. Hearing Research 18, 159–168 (1985)CrossRefGoogle Scholar
- 29.International Phonetic Association, ed.: Handbook of the International Phonetic Association. Cambridge University Press, Cambridge, UK (1999), Available at http://web.uvic.ca/ling/resources/ipa/handbook.htm
- 30.Adelson, E.H., Bergen, J.R.: Spatiotemporal energy models for the perception of motion. J. Opt. Soc. Am. A 2(2), 284–299 (1985)CrossRefGoogle Scholar
- 31.Rioul., O., Vetterli, M.: Wavelets and signal processing. IEEE Signal Processing Magazine 8, 14–38 (1991)CrossRefGoogle Scholar
- 32.Hudspeth, A.J.: Hearing. In: Kandel, E.R., Schwartz, J.H., Jessell, T.M. (eds.) Principles of Neural Science, 4th edn., pp. 590–613. McGraw-Hill, New York (2000)Google Scholar
- 33.Depireux, D.A., Simon, J.Z., Klein, D.J., Shamma, S.A.: Spectro-temporal response field characterization with dynamic ripples in ferret primary auditory cortex. J. Neurophysiol 85(3), 1220–1234 (2001)Google Scholar
- 34.Klein, D.J., Simon, J.Z., Depireux, D.A., Shamma, S.A.: Stimulus-invariant processing and spectrotemporal reverse correlation in primary auditory cortex. J. Comput Neurosci 20(2), 111–136 (2006)MATHCrossRefGoogle Scholar
- 35.Theunissen, F.E., Woolley, S.M.N., Hsu, A., Fremouw, T.: Methods for the analysis of auditory processing in the brain. Ann. N. Y. Acad. Sci. 1016, 187–207 (2004)CrossRefGoogle Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2007