nips nips2012 nips2012-195 nips2012-195-reference knowledge-graph by maker-knowledge-mining

195 nips-2012-Learning visual motion in recurrent neural networks


Source: pdf

Author: Marius Pachitariu, Maneesh Sahani

Abstract: We present a dynamic nonlinear generative model for visual motion based on a latent representation of binary-gated Gaussian variables. Trained on sequences of images, the model learns to represent different movement directions in different variables. We use an online approximate inference scheme that can be mapped to the dynamics of networks of neurons. Probed with drifting grating stimuli and moving bars of light, neurons in the model show patterns of responses analogous to those of direction-selective simple cells in primary visual cortex. Most model neurons also show speed tuning and respond equally well to a range of motion directions and speeds aligned to the constraint line of their respective preferred speed. We show how these computations are enabled by a specific pattern of recurrent connections learned by the model. 1


reference text

[1] A Mikami, WT Newsome, and RH Wurtz. Motion selectivity in macaque visual cortex. II. Spatiotemporal range of directional interactions in MT and V1. Journal of Neurophysiology, 55(6):1328–1339, 1986.

[2] MS Livingstone. Mechanisms of direction selectivity in macaque V1. Neuron, 20:509–526, 1998.

[3] LF Abbott and KI Blum. Functional significance of long-term potentiation for sequence learning and prediction. Cerebral Cortex, 6:406–416, 1996.

[4] RPN Rao and TJ Sejnowski. Predictive sequence learning in recurrent neocortical circuits. Advances in Neural Information Processing, 12:164–170, 2000.

[5] B Olshausen. Learning sparse, overcomplete representations of time-varying natural images. IEEE International Conference on Image Processing, 2003.

[6] P Berkes, RE Turner, and M Sahani. A structured model of video produces primary visual cortical organisation. PLoS Computational Biology, 5, 2009.

[7] L Wiskott and TJ Sejnowski. Slow feature analysis: Unsupervised learning of invariances. Neural Computation, 14(4):715–770, 2002.

[8] C Cadieu and B Olshausen. Learning transformational invariants from natural movies. Advances in Neural Information Processing, 21:209–216, 2009.

[9] D Barber. Learning in spiking neural assemblies. Advances in Neural Information Processing, 15, 2002.

[10] J Brea, W Senn, and JP Pfister. Sequence learning with hidden units in spiking neural networks. Advances in Neural Information Processing, 24, 2011.

[11] RP Rao and Ballard DH. Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nature Neuroscience, 2(1):79–87, 1999.

[12] K Friston. A theory of cortical responses. Phil. Trans. R. Soc. B, 360(1456):815–836, 1999.

[13] RJ Douglas, C Koch, M Mahowald, KA Martin, and HH Suarez. Recurrent excitation in neocortical circuits. Science, 269(5226):981–985, 1995.

[14] TP Minka. Expectation propagation for approximate Bayesian inference. UAI’01 Proceedings of the Seventeenth conference on Uncertainty in artificial intelligence, pages 362–369, 2001.

[15] A Doucet, N Freitas, K Murphy, and S Russell. Rao-blackwellised particle filtering for dynamic Bayesian networks. UAI’00 Proceedings of the Sixteenth conference on Uncertainty in artificial intelligence, pages 176–183, 2000.

[16] M Rehn and FT Sommer. A network that uses few active neurones to code visual input predicts the diverse shapes of cortical receptive fields. Journal of Computational Neuroscience, 22:135–146, 2007.

[17] IJ Goodfellow, A Courville, and Y Bengio. Spike-and-slab sparse coding for unsupervised feature discovery. arXiv:1201.3382v2, 2012.

[18] BA Olshausen and KJ Millman. Learning sparse codes with a mixture-of-Gaussians prior. Advances in Neural Information Processing, 12, 2000.

[19] SG Mallat and Z Zhang. Matching pursuits with time-frequency dictionaries. IEEE Transactions on Signal Processing, 41(12):3397–3415, 1993.

[20] BA Olshausen and DJ Field. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381:607–609, 1996.

[21] MR Peterson, B Li, and RD Freeman. The derivation of direction selectivity in the striate cortex. Journal of Neuroscience, 24:35833591, 2004.

[22] GA Orban, H Kennedy, and J Bullier. Velocity sensitivity and direction selectivity of neurons in areas V1 and V2 of the monkey: influence of eccentricity. Journal of Neurophysiology, 56(2):462–480, 1986.

[23] EP Simoncelli and DJ Heeger. A model of neuronal responses in visual area MT. Vision Research, 38(5):743–761, 1998.

[24] WH Bosking, Y Zhang, B Schofield, and D FitzPatrick. Orientation selectivity and the arrangement of horizontal connections in tree shrew striate cortex. Journal of Neuroscience, 17(6):2112–2127, 1997.

[25] SI Fried, TA Munch, and FS Werblin. Directional selectivity is formed at multiple levels by laterally offset inhibition in the rabbit retina. Neuron, 46(1):117–127, 2005.

[26] Y Li, D FitzPatrick, and LE White. The development of direction selectivity in ferret visual cortex requires early visual experience. Nature Neuroscience, 9(5):676–681, 2006.

[27] S Xu, W Jiang, M Poo, and Y Dan. Activity recall in a visual cortical ensemble. Nature Neuroscience, 15:449–455, 2012. 9