nips nips2002 nips2002-206 nips2002-206-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Robert A. Jacobs, Melissa Dominguez
Abstract: We consider the hypothesis that systems learning aspects of visual perception may benefit from the use of suitably designed developmental progressions during training. Four models were trained to estimate motion velocities in sequences of visual images. Three of the models were “developmental models” in the sense that the nature of their input changed during the course of training. They received a relatively impoverished visual input early in training, and the quality of this input improved as training progressed. One model used a coarse-to-multiscale developmental progression (i.e. it received coarse-scale motion features early in training and finer-scale features were added to its input as training progressed), another model used a fine-to-multiscale progression, and the third model used a random progression. The final model was nondevelopmental in the sense that the nature of its input remained the same throughout the training period. The simulation results show that the coarse-to-multiscale model performed best. Hypotheses are offered to account for this model’s superior performance. We conclude that suitably designed developmental sequences can be useful to systems learning to estimate motion velocities. The idea that visual development can aid visual learning is a viable hypothesis in need of further study.
[1] Geman, S., Bienenstock, E., and Doursat, R. (1995) Neural networks and the bias/variance dilemma. Neural Computation, 4, 1-58.
[2] Dominguez, M. and Jacobs, R.A. (2003) Developmental constraints aid the acquisition of binocular disparity sensitivities. Neural Computation, in press.
[3] Ohzawa, I., DeAngelis, G.C., and Freeman, R.D. (1990) Stereoscopic depth discrimination in the visual cortex: Neurons ideally suited as disparity detectors. Science, 249, 1037-1041.
[4] Adelson, E.H. and Bergen, J.R. (1985) Spatiotemporal energy models for the perception of motion. Journal of the Optical Society of America A, 2, 284-299.
[5] Heeger, D.J. (1992) Normalization of cell responses in cat striate cortex. Visual Neuroscience, 9, 181-197.
[6] Nowlan, S.J. and Sejnowski, T.J. (1994) Filter selection model for motion segmentation and velocity integration. Journal of the Optical Society of America A, 11, 3177-3200.
[7] Press, W.H., Teukolsky, S.A., Vetterling, W.T., and Flannery, B.P. (1992) Numerical Recipes in C: The Art of Scientific Computing. Cambridge, UK: Cambridge University Press.
[8] Jacobs, R.A. and Dominguez, M. (2003) Visual development and the acquisition of motion velocity sensitivities. Neural Computation, in press.
[9] Weiss, Y. and Adelson, E.H. (1998) Slow and smooth: A Bayesian theory for the combination of local motion signals in human vision. Center for Biological and Computational Learning Paper Number 158, Massachusetts Institute of Technology, Cambridge, MA.
[10] Milner, P.M. (1974) A model for visual shape recognition. Psychological Review, 81, 521-535.
[11] Hinton, G.E. (1981) Shape representation in parallel systems. In A. Drina (Ed.), Proceedings of the Seventh International Joint Conference on Artificial Intelligence.
[12] Ballard, D.H. (1986) Cortical connections and parallel processing: Structure and function. Behavioral and Brain Sciences, 9, 67-120.