Learning low-dimensional representations via the usage of multiple-class labels

References

• Atick J J, Griffin P A, Redlich A N. The vocabulary of shape: principal shapes for probing perception and neural response. Network: Comput. Neural Syst. 1996; 7: 1–5
   PubMed Web of Science ®Google Scholar
• Baldi P, Hornik K. Neural networks and principal component analysis: Learning from examples without local minima. Neural Networks 1989; 2: 53–8
   Web of Science ®Google Scholar
• Baxt W G, White H. Bootstrapping confidence intervals for clinical input variable effects in network trained to identify the presence of acute myocardial infraction. Neural Comput. 1995; 7: 624–38
   PubMed Web of Science ®Google Scholar
• Bellman R E. Adaptive Control Processes. Princeton University Press, Princeton, NJ 1961
   Google Scholar
• Borg I, Lingoes J. Multidimensional Similarity Structure Analysis. Springer, Berlin 1987
   Google Scholar
• Breiman L. Stacked regression. Technical Report TR-367. Department of Statistics, University of California, Berkeley 1992
   Google Scholar
• Breiman L. Bagging predictors. Technical Report TR-421. Department of Statistics, University of California, Berkeley 1994
   Google Scholar
• Buckheit J, Donoho D L. Improved linear discrimination using time-frequency dictionaries. Technical Report. Stanford University. 1995
   Google Scholar
• Busey T A, Brady N P, Cutting J E. Compensation is unnecessary for the perception of faces in slanted pictures. Perception Psychophys. 1990; 48: 1–11
   PubMed Web of Science ®Google Scholar
• Caruana R. Multitask connectionist learning. Proc. 1993 Connectionist Models Summer School. Morgan Kaufmann, San Mateo, CA 1993; 372–9
   Google Scholar
• Caruana R. Learning many related tasks at the same time with backpropagation. Advances in Neural Information Processing Systems 7, G Tesauro, D Touretzky, T Leen. Morgan Kaufmann, San Mateo, CA 1995; 657–64, pp 657–64
   Google Scholar
• Caruana R, de Sa V R. Promoting poor features to supervisors: Some inputs work better as outputs. Advances in Neural Information Processing Systems 9, M C Mozer, M I Jordan, T Petsche. Morgan Kaufmann, San Mateo, CA 1997
   Google Scholar
• Cortese J M, Dyre B P. Perceptual similarity of shapes generated from Fourier Descriptors. J. Exp. Psychol: Human Percept. Perform. 1996; 22: 133–43
   PubMed Web of Science ®Google Scholar
• Cottrell G W, Munro P, Zipser D. Learning internal representations from gray-scale images: An example of extensional programming. Proc. 9th Ann. Conf.of the Cognitive Science Society. Erlbaum, Hillsdale, NJ 1987; 462–73
   Google Scholar
• Cutzu F, Edelman S. Faithful representation of similarities among three-dimensional shapes in human vision. Proc. Natl Acad. Sci. USA 1996; 93: 12046–50
   PubMed Web of Science ®Google Scholar
• Demartines P, Hérault J. Curvilinear component analysis: a self-organizing neural network for non linear mapping of data sets. IEEE Trans. Neural Networks 1996, submitted
   Web of Science ®Google Scholar
• DeMers D, Cottrell G. Nonlinear dimensionality reduction. Advances in Neural Information Processing Systems 5, S J Hanson, J D Cowan, C L Giles. Morgan Kaufmann, San Mateo, CA 1993; 580–7
   Google Scholar
• Edelman S. Representation of similarity in 3D object discrimination. Neural Comput. 1995a; 7: 407–22
   Google Scholar
• Edelman S. Representation, similarity, and the chorus of prototypes. Minds Machines 1995b; 5: 45–68
   Web of Science ®Google Scholar
• Edelman S. Representation is representation of similarity. Behav. Brain Sci. 1997, in press
   Google Scholar
• Edelman S, Cutzu F, Duvdevani-Bar S. Similarity to reference shapes as a basis for shape representation. Proc. 18th Ann. Conf. of Cognitive Science Society, San Diego, CA. G W Cottrell. Erlbaum, Hillsdale, NJ 1996; 260–5
   Google Scholar
• Edelman S, Duvdevani-Bar S. A model of visual recognition and categorization. Phil. Trans. R. Soc. Lond. B 1997a; 352, in press
   PubMed Web of Science ®Google Scholar
• Edelman S, Duvdevani-Bar S. Similarity, connectionism, and the problem of representation in vision. Neural Comput. 1997b; 9: 701–20
   PubMed Web of Science ®Google Scholar
• Efron B, Tibshirani R. An Introduction to the Bootstrap. Chapman and Hall, London 1993
   Google Scholar
• Elman J L, Zipser D. Learning the hidden structure of speech. J. Acoust. Soc. Am. 1988; 4: 1615–26
   Google Scholar
• Fisher R A. The use of multiple measurements in taxonomic problems. Ann. Eugenics 1936; 7: 179–88
   Google Scholar
• Grossman T, Lapedes A. Use of bad training data for better prediction. Advances in Neural Information Processing Systems 6, J D Cowan, G Tesauro, J Alspector. Morgan Kaufmann, San Mateo, CA 1993; 342–50
   Google Scholar
• Intrator N. Combining exploratory projection pursuit and projection pursuit regression with application to neural networks. Neural Comput. 1993; 5: 443–55
   Web of Science ®Google Scholar
• Intrator N, Edelman S. How to make a low-dimensional representation suitable for diverse tasks. Connect. Sci. 1996; 8: 205–24
   Google Scholar
• Koontz W L G, Fukunaga K. A nonlinear feature extraction algorithm using distance information. IEEE Trans. Comput. 1972; C-21: 56–63
   Web of Science ®Google Scholar
• Kruskal J B. Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis. Psychometrika 1964; 29: 1–27
   Web of Science ®Google Scholar
• Lando M, Edelman S. Receptive field spaces and class-based generalization from a single view in face recognition. Network: Comput. Neural Syst. 1995; 6: 551–76
   Web of Science ®Google Scholar
• LeBlanc M, Tibshirani R. Combining estimates in regression and classification. Stanford University. 1994, Preprint
   Google Scholar
• Leen T K, Kambhatla N. Fast non-linear dimension reduction. Advances in Neural Information Processing Systems 6, J D Cowan, G Tesauro, J Alspector. Morgan Kaufmann, San Mateo, CA 1994; 152–9
   Google Scholar
• Lowe D. Novel ‘topographic’ nonlinear feature extraction using radial basis functions for concentration codeing in the ‘artificial nose’. Proc. 3rd IEE Int. Conf. on Artificial Neural Networks. IEE, Stevenage 1993
   Google Scholar
• Lowe D, Tipping M E. Feed-forward neural networks and topographic mappings for exploratory data analysis. Neural Computing Appl. 1996; 4: 83–95
   Web of Science ®Google Scholar
• Nowlan S J, Hinton G E. Simplifying neural networks by soft weight-sharing. Neural Comput. 1992; 4: 473–93
   Web of Science ®Google Scholar
• Oja E. Neural networks, principal components, and subspaces. Int. J. Neural Syst. 1989; 1: 61–8
   Google Scholar
• Pickover C. Computers, Pattern, Chaos, and Beauty. St.Martin's Press, New York 1990
   Google Scholar
• Poggio T, Girosi F. Regularization algorithms for learning that are equivalent to multilayer networks. Science 1990; 247: 978–82
   PubMed Web of Science ®Google Scholar
• Price D, Knerr S, Personnaz L, Dreyfus G. Pairwise neural network classifiers with probabilistic outputs. Advances in Neural Information Processing 7, G Tesauro, D S Touretsky, T K Leen. MIT Press, Cambridge, MA 1995; 1109–16
   Google Scholar
• Raviv Y, Intrator N. Bootstrapping with noise: An effective regularization technique. Connect. Sci. 1996; 8: 356–72
   Google Scholar
• Sammon J W. A nonlinear mapping for data structure analysis. IEEE Trans. Comput. 1969; C-18: 401–9
   Web of Science ®Google Scholar
• SAS. SAS/STAT, User's Guide, Version 6. NC, SAS Institute Inc, Cary 1989
   Google Scholar
• Shepard R N. Metric structures in ordinal data. J. Math. Psychol. 1966; 3: 287–15
   Web of Science ®Google Scholar
• Shepard R N. Multidimensional scaling, tree-fitting, and clustering. Science 1980; 210: 390–7
   PubMed Web of Science ®Google Scholar
• Shepard R N, Cermak G W. Perceptual-cognitive explorations of a toroidal set of free-form stimuli. Cogn. Psychol. 1973; 4: 351–77
   Web of Science ®Google Scholar
• Siedlecki W, Siedlecka K, Sklansky J. An overview of mapping techniques for exploratory pattern analysis. Pattern Recogn. 1988; 21: 411–29
   Web of Science ®Google Scholar
• Simard P, Victorri B, LeCun Y, Denker J. Tangent prop-a formalism for specifying selected invariances in an adaptive network. Neural Information Processing Systems 4, J Moody, R Lippman, S J Hanson. Morgan Kaufmann, San Mateo, CA 1992; 895–903
   Google Scholar
• Stone M. Cross-validatory choice and assessment of statistical predictions (with discussion). J. R. Stat. Soc. B 1974; 36: 111–47
   Google Scholar
• Thrun S, Mitchell T. Learning one more thing. Proc. 14th Int. Joint Conf. on Artificial Intelligenc, C Mellish. Morgan Kaufmann, San Mateo, CA 1995; vol 2: 1217–23
   Google Scholar
• Wahba G. Splines Models for Observational (Data Series in Applied Mathematics 59). SIAM, Philadelphia, PA 1990
   Google Scholar
• Webb A R. Multidimensional-scaling by iterative majorization using radial basis functions. Pattern Recogn. 1995; 28: 753–9
   Web of Science ®Google Scholar
• Young G, Householder A S. Discussion of a set of points in terms of their mutual distances. Psychometrika 1938; 3: 19–22
   Google Scholar