References

Sanger 1994d

Sanger T. D., 1994d, Optimal unsupervised motor learning for dimensionality reduction of nonlinear control systems, IEEE Trans. Neural Networks, 5(6):965--973.

Sanger 1994c

Sanger T. D., 1994c, Two algorithms for iterative computation of the singular value decomposition from input/output samples, In Hanson S. J., Cowan J. D., Giles C. L., ed.s, Advances in Neural Information Processing Systems 6, Morgan Kaufmann, San Mateo, CA, in press.

Sanger 1994b

Sanger T. D., 1994b, Optimal unsupervised motor learning predicts the internal representation of barn owl head movements, In Hanson S. J., Cowan J. D., Giles C. L., ed.s, Advances in Neural Information Processing Systems 6, Morgan Kaufmann, San Mateo, CA, in press.

Sanger 1994a

Sanger T. D., 1994a, Using the generalization properties of a neural network to infer the number and shape of its hidden units, in preparation.

Dornay and Sanger 1993d

Dornay M., Sanger T. D., 1993d, Equilibrium point control of a monkey arm simulator by a fast learning artificial neural network.

Sanger 1993c

Sanger T. D., 1993c, Trajectory relaxation learning, IEEE Trans. Robotics and Automation, in press.

Sanger 1993b

Sanger T. D., 1993b, A practice strategy for robot learning control, In Hanson S. J., Cowan J. D., Giles C. L., ed.s, Advances in Neural Information Processing Systems 5, pages 335--341, Morgan Kaufmann, San Mateo, CA, Proc. NIPS'92, Denver CO.

Sanger 1993a

Sanger T. D., 1993a, Theoretical Elements of Hierarchical Control in Vertebrate Motor Systems, PhD thesis, MIT.

Sanger 1992b

Sanger T. D., 1992b, Theoretical considerations for the analysis of population coding in motor cortex, Neural Computation, in press.

Sanger et al. 1992a

Sanger T. D., Sutton R., Matheus C., 1992a, Iterative construction of sparse polynomial approximations, In Moody J. E., Hanson S. J., Lippmann R. P., ed.s, Advances in Neural Information Processing Systems 4, Morgan Kaufmann, San Mateo, CA, Proc. NIPS'91, Denver CO.

Sanger 1991e

Sanger T. D., 1991e, A tree-structured algorithm for reducing computation in networks with separable basis functions, Neural Computation, 3(1):67--78.

Sanger 1991d

Sanger T. D., 1991d, Optimal hidden units for two-layer nonlinear feedforward neural networks, International Journal of Pattern Recognition and Artificial Intelligence, 5(4):545--561, Also appears in C. H. Chen, ed., Neural Networks in Pattern Recognition and Their Applications, World Scientific, 1991, pp. 43-59.

Sanger 1991c

Sanger T. D., 1991c, A tree-structured adaptive network for function approximation in high dimensional spaces, IEEE Trans. Neural Networks, 2(2):285--293.

Sanger 1991b

Sanger T. D., 1991b, Basis-function trees as a generalization of local variable selection methods for function approximation, In Lippmann R. P., Moody J. E., Touretzky D. S., ed.s, Advances in Neural Information Processing Systems 3, pages 700--706, Morgan Kaufmann, Proc. NIPS'90, Denver CO.

Sanger 1991a

Sanger T. D., 1991a, Using LMS trees for image processing, In Proc. Int'l Joint Conf. Neural Networks, volume II, pages 405--410, IEEE Press, New York.

Sanger 1990d

Sanger T. D., 1990d, Analysis of the two-dimensional receptive fields learned by the generalized Hebbian algorithm in response to random input, Biological Cybernetics, 63:221--228.

Sanger 1990c

Sanger T. D., 1990c, Learning nonlinear features using eigenvectors of radial basis functions, Abstracts of the Neural Networks for Computing conference, Snowbird UT.

Sanger 1990b

Sanger T. D., 1990b, Basis-function trees for approximation in high-dimensional spaces, In Touretzky D., Elman J., Sejnowski T., Hinton G., ed.s, Proceedings of the 1990 Connectionist Models Summer School, pages 145--151, Morgan Kaufmann, San Mateo, CA.

Sanger 1990a

Sanger T. D., 1990a, A theoretical analysis of population coding in motor cortex, In Antognetti P., Milutinovic V., ed.s, Neural Networks: Concepts, Applications, and Implementations, volume 2, Prentice Hall, New Jersey.

Sanger 1989c

Sanger T. D., 1989c, Optimal unsupervised learning in a single-layer linear feedforward neural network, Neural Networks, 2:459--473.

Sanger 1989b

Sanger T. D., 1989b, Optimal unsupervised learning in feedforward neural networks, MIT AI Lab Tech. Report 1086.

Sanger 1989a

Sanger T. D., 1989a, An optimality principle for unsupervised learning, In Touretzky D. S., ed., Advances in Neural Information Processing Systems 1, pages 11--19, Morgan Kaufmann, San Mateo, CA, Proc. NIPS'88, Denver.

Sanger 1988b

Sanger T. D., 1988b, Stereo disparity computation using Gabor filters, Biological Cybernetics, 59:405--418.

Sanger 1988a

Sanger T. D., 1988a, Optimal unsupervised learning, Neural Networks, 1(S1):127, Proc. 1st Ann. INNS meeting, Boston, MA.

Sanger 1985

Sanger T. D., 1985, The use of gabor filters for understanding changing images, A.B. Thesis, Harvard College.