References
F. Girosi
References in Federico Girosi's home page:
here,
which include an electronic version of his
slides.
G. Dreyfus
- O. Nerrand, P. Roussel-Ragot, L. Personnaz, G. Dreyfus, and S. Marcos,
"Neural Networks and Non-Linear Adaptive Filtering: Unifying Concepts
and New Algorithms",
Neural Computation, vol.5, pp. 165-197, 1993
- I. Rivals, L. Personnaz, G. Dreyfus, and J.L. Ploix,
"Modélisation, classification et commande par réseaux
de neurones: principes fondamentaux, méthodologie de conception
et applications industrielles",
Récents Progrès en Génie des
Procédés, vol. 9, Lavoisier Technique et Documentation,
Paris, 1995
- O. Nerrand, P. Roussel-Ragot, D. Urbani, L. Personnaz, and G. Dreyfus,
"Training Recurrent Neural Networks: How and Why? An Illustration in
Dynamical Process Modeling",
IEEE Transactions on Neural Networks, vol. 5, pp. 178-184, 1994
- I. Rivals, and L. Personnaz,
"Black-box modeling with state-space neural networks",
Neural Adaptive Control Technology, R. Zbikowski
and K.J. Hunt, eds, World Scientific, 1996
- J.L. Ploix, G. Dreyfus, J.P. Corriou, and D. Pascal,
"From Knowledge-based Models to Recurrent Networks: an Application to
an Industrial Distillation Process",
Neural Networks and their Applications, J. Hérault, ed, 1994
- J.L. Ploix, and G. Dreyfus,
"Knowledge-based Neural Modeling: Principles and Industrial
Applications", Proc. ICANN'95
back to the abstracts
- N. Intrator, and L.N. Cooper,
"Objective Function Formulation of the BCM Theory of
Visual Cortical Plasticity: Statistical Connections,
Stability Conditions",
Neural Networks, (5), pp. 3-17, 1992
- N. Intrator,
"Combining Exploratory Projection Pursuit and Projection Pursuit Regression",
Neural Computation, (5), pp. 443-455, 1993
- N. Intrator, and S. Edelman,
"How to make a low-dimensional representation suitable for diverse tasks",
To appear: Connection Science, Speciall issue on Transfer in Neural Networks
- Y. Raviv, and N. Intrator,
"Bootstrapping with Noise: An Effective Regularization Technique"
back to the abstracts
- S.I. Gallant,
"Three constructive algorithms for network learning",
Proc. 8th Ann Conf of Cognitive Science Soc, pp. 652-660,
Amherst, MA 15-17 august 1986, 1986
- P. Rujan, and M. Marchand,
"Learning by minimizing resources in neural networks",
Complex Systems, 3, pp.229-242, 1989
- M. Mézard, and J.-P. Nadal,
"Learning in feedforward layered networks: the tiling algorithm",
J. Phys. A: Math. and Gen., 22, pp.2191-2203, 1989
- M. Bichsel, and P. Seitz,
"Minimum class entropy: a maximum information approach to layered networks",
Neural Networks, 2, pp. 133-141, 1989
- M. Frean,
"The upstart algorithm: a method for constructing and training
feedforward neural networks",
Neural Computation, 2, pp. 198-209, 1990
- S. Knerr, L. Personnaz, and G. Dreyfus,
"Single layer learning revisited: a stepwise procedure for building
and training a neural network",
In F. Fogelman and J. Hérault, editors,
Proc. NATO workshop Les Arcs 1989, Springer, 1989
- T. Grossman, R. Meir, and E. Domany,
"Learning by choice of internal representations",
Complex Systems, 2, pp. 2-555, 1988
- J.A. Sirat, and J.-P. Nadal,
"Neural trees: a new tool for classification",
Network, 1, pp. 423-438, 1990
- M. Golea, and M. Marchand,
"A growth algorithm for neural network decision trees",
Europhys. Lett., 12, pp. 105-110, 1990
- M.I. Jordan, and R.A. Jacobs,
"Hierarchical mixtures of experts and the em algorithm",
Neural Computation, 6, pp. 181-214, 1994
- F. d'Alché Buc, D. Zwierski, and J.-P. Nadal,
"Trio learning: a new strategy for building hybrid trees",
Int. Journ. of Neur. Syst., 5, pp. 259-274, 1994
- F. d'Alché Buc, and J.-P. Nadal,
"Asymptotic performance of a constructive algorithm",
Neural Processing Letters, 1, pp. 1-4, 1995
back to the abstracts
back to the abstracts
- S. Bengio,
"Input/Output Hidden Markov Models",
Slides of a presentation at the Montreal Workshop and Spring School
on Artifical Neural Networks and Learning Algorithms,1996
- Y. Bengio, and P. Frasconi,
"An Input/Output HMM Architecture",
In G. Tesauro, D.S. Touretzky, and T.K. Leen, editors,
Advances in Neural Information Processing Systems 7, pp. 427-434,
MIT Press, Cambridge, MA, 1995
- Y. Bengio, and P. Frasconi,
"Input/Output HMMs for Sequence Processing",
submitted for publication, 1996
- S. Bengio, and Y. Bengio,
"An EM Algorithm for Asynchronous Input/Output Hidden Markov Models",
ICONIP'96, 1996
- Y. Bengio, and P. Frasconi,
"Diffusion of Context and Credit Information in Markovian Models",
Journal of Artificial Intelligence Research, 3, pp. 223-244, 1995
back to the abstracts
- A good place to start to learn about the most popular
algorithm for general inference in graphical models, as well
as some of the basics on learning:
D. J. Spiegelhalter, A. P. Dawid, S. L. Lauritzen, and R.G. Cowell,
"Bayesian Analysis in Expert Systems",
Statistical Science, 8, pp. 219-283, 1993
- If you want more details on the inference algorithm:
S. L. Lauritzen, and D. J. Spiegelhalter,
"Local computations with probabilities on graphical
structures and their application to expert systems"
(with discussion),
Journal of the Royal Statistical Society B,
50, pp. 157-224, 1988
- A tutorial on the recent work on learning in graphical models:
D. Heckerman,
"A tutorial on learning Bayesian networks", 1995,
[available through http://www.auai.org]
- If you want more on learning:
W. Buntine,
"Operations for Learning with Graphical Models",
Journal of Artificial Intelligence Research 2,
pp. 159-225, 1994, [available through http://www.auai.org]
- A very readable general textbook on graphical models from a statistical
perspective (focusing on ML estimation and model selection):
J. Whittaker,
Graphical Models in Applied Multivariate Statistics,
New York: John Wiley, 1990
- An introductory textbook:
E. Neapolitan,
Probabilistic Reasoning in Expert Systems,
New York: John Wiley, 1990
- The classical text on graphical models; emphasizes inference
and AI issues:
J. Pearl,
Probabilistic Reasoning in Intelligent Systems: Networks of Plausible
Inference, San Mateo, CA: Morgan Kaufman, 1988
- A recent paper that unifies (almost) all of the extant
algorithms for inference in graphical models:
R. D. Shachter, S. K. Anderson, and P. Szolovits,
"Global conditioning for probabilistic inference in belief networks",
Proceedings of the Uncertainty in Artificial Intelligence Conference,
pp. 514-522, 1994
back to the abstracts
- S. Becker,
"Mutual Information Maximization: Models of Cortical Self-Organization",
Network: Computation in Neural Systems, 7:7-31, 1996
- S. Becker, and M. Plumbley,
"Unsupervised Neural Network Learning Procedures For Feature
Extraction and Classification",
International Journal of Applied Intelligence, special issue on neural networks,
(F. Pineda, ed.), Vol. 6, No. 3, 1996
- S. Becker,
"JPMAX: Learning to Recognize Moving Objects as a Model-fitting Problem",
Advances in Neural Information Processing Systems 7, pp. 933-940,
San Mateo, CA: Morgan Kaufmann Publishers, 1995
- S. Becker,
"An unsupervised classifier modulated by temporal history outperforms
recurrent back-propagation in face recognition",
Proceedings of the Machines That Learn workshop in Snowbird, Utah (abstract only),
1996
- R.A. Jacobs, M.I. Jordan, S.J. Nowlan, and G.E. Hinton,
"Adaptive mixtures of local experts",
Neural Computation, 3(1):79-87, 1991
- R. Linsker,
"Self-organization in a perceptual network",
IEEE Computer, Volume 21 (March), pp. 105-117, 1988
- S.J. Nowlan,
"Maximum likelihood competitive learning",
Advances in Neural Information Processing Systems 2,
pp. 574-582, D.S. Touretzky (ed), San Mateo, CA: Morgan Kaufmann, 1990
- E. Oja,
"A Simplified Neuron Model As A Principal Component Analyzer",
Journal of Mathematical Biology, 15(3):267-273, 1982
- E. Oja,
"Neural Networks, Principal Components, and Subspaces",
International Journal Of Neural Systems, 1(1):61-68, 1989
- D.A. Pomerleau,
"Input Reconstruction Reliability Estimation",
Advances in Neural Information Processing Systems 5,
pp. 279-286, S. J. Hanson, J. D. Cowan, and C. L. Giles (eds), Morgan Kaufmann, 1993
- T.D. Sanger,
"Optimal Unsupervised Learning in a Single-Layer Linear Feedforward Neural Network",
Neural Networks, 2:459-473, 1989
back to the abstracts
All papers can be recovered at
DSI Labs
- Optimal convergence of on-line Backprop - The analysis is based on
an extension of Rosenblatt's PC-Theorem:
M. Gori, and M. Maggini,
"Optimal convergence of on-line Backpropagation",
IEEE Transactions on Neural Networks,
vol. 7, no. 1, pp. 251-254, January 1996
- Paper containing a general analysis of the problem of local minima
in Backprop in the case of pyramidal nets:
M. Gori, and A. Tesi,
"On the Problem of Local Minima in Backpropagation",
IEEE Trans. on Patt. Anal. and Mach. Intell.,
vol. 14, no. 1, pp. 76-86, January 1992
- Paper containing a general analysis of the problem of local minima
in Backprop in the case of pyramidal nets:
M. Bianchini, P. Frasconi, and M. Gori,
"Learning without local minima in radial basis function networks",
IEEE Trans. on Neural Networks, vol. 6, no. 3,
pp. 749-756, May 1995
- General analysis of local minima in the case of recurrent nets:
M. Bianchini, M. Gori, and M. Maggini,
"On the Problem of Local Minima in Recurrent Networks",
IEEE Transactions on Neural Networks,
vol. 5, no. 2, pp. 167-177, March 1994
- A survey on the problem of optimal convergence with more than 80 references
M. Bianchini, and M. Gori,
"Optimal Learning in Artificial Neural Networks: A review of theoretical results",
Neurocomputing, to appear
An Introduction to Suspiciousness - Part II:
A general approach to learning and problem solving
- M. Bianchini, S. Fanelli, M. Gori, and M. Protasi,
"Unimodal loading problems",
Annals of Mathematics and Artificial Intelligence, to appear
- P. Frasconi, S. Fanelli, and M. Protasi,
"Suspiciousness of loading problems",
International Conference on Neural Networks,
Washington, 1996, to appear
back to the abstracts
- A. Frosini, M. Gori, and L. Pistolesi,
"Number-Plate Recognition in Practice: The role of Neural Networks",
ICANN95 - (industrial track), Paris, 1995
- M. Bianchini, P. Frasconi, and M. Gori,
"Learning in Multilayered Networks Used as Autoassociators",
IEEE Trans. on Neural Networks,
vol. 6, no. 2, pp. 512-515, March 1995
- M. Gori, L. Lastrucci, and G. Soda,
"Autoassociator-Based Models for Speech Verification",
Pattern Recognition Letters, to appear
- A. Frosini, M. Gori, and P. Priami,
"A Neural Network-Based Model for Paper Currency Recognition and Verification",
IEEE Trans. on Neural Networks, to appear
back to the abstracts
- T. Hastie, R. Tibshirani, and A. Buja,
"Flexible Discriminant Analysis by Optimal Scoring", 1993
- T. Hastie, and R. Tibshirani,
"Discriminant Analysis by Gaussian Mixtures",
to appear in the Journal of the Royal Statistical Society, series B, 1994
- T. Hastie, A. Buja, and R. Tibshirani,
"Penalized Discriminant Analysis", 1994
- T. Hastie, and R. Tibshirani,
"Discriminant Adaptive Nearest Neighbor Classification", 1994
back to the abstracts
back to the abstracts
- L. Breiman,
"Better subset selection using the non-negative garotte",
Technical report, Univ. of Cal., Berkeley, 1993
- C. Daniel, and F. Wood
Fitting equations to data,
Wiley, New York, 1980
- D. Donoho, and I. Johnstone,
"Adapting to unknown smoothness via wavelet shrinkage",
Technical report, Stanford University, 1993
- B. Efron, and R. Tibshirani,
An Introduction to the Bootstrap,
Chapman and Hall, 1993
- J. Friedman,
"Multivariate adaptive regression splines" (with discussion),
Annals of Statistics, vol. 19, no. 1, pp. 1-141, 1991
- E. George, and R. McCulloch,
"Variable selection via gibbs sampling",
J. Amer. Statist. Assoc., vol. 88, pp. 884-889, 1993
- T. Hastie, and R. Tibshirani,
Generalized Additive Models,
Chapman and Hall, 1990
- C. Lawson, and R. Hansen,
Solving least squares problems,
Prentice-Hall, 1974
- C. Stein,
"Estimation of the mean of a multivariate normal distribution",
Ann. Statist., vol. 9, pp. 1135-1151, 1981
- L. Breiman,
"Bagging predictors",
Technical report, University of California- Berkeley, 1994
- L. Breiman, J. Friedman, R. Olshen, and C. Stone,
Classification and Regression Trees,
Wadsworth, 1984
- L. Clark, and D. Pregibon,
"Tree-based models",
In J. Chambers, and T. Hastie, eds,
Statistical models in S,
Wadsworth, 1991
- B. Efron,
"Bootstrap methods: another look at the jackknife",
Annals of Statistics, vol. 7, pp. 1-26, 1979
- B. Efron, and R. Tibshirani,
An Introduction to the Bootstrap,
Chapman and Hall, 1993
- P. Hall,
The Bootstrap and Edgeworth Expansion,
Springer-Verlag, 1992
- T. Hastie, and R. Tibshirani,
Generalized Additive Models,
Chapman and Hall, 1990
- P. Rousseeuw,
"Least median of squares regression",
J. Amer. Statist. Assoc., vol. 79, pp. 871-880, 1984
back to the abstracts
P. Dayan
- H. B. Barlow,
"Unsupervised Learning",
Neural Computation, vol. 1, pp. 295-311, 1989
- P. Dayan, and G. E. Hinton,
"Varieties of Helmholtz Machine",
Neural Networks, 1996, in press
- P. Dayan, G. E. Hinton, R. M. Neal, and R. S. Zemel,
"The Helmholtz machine",
Neural Computation, vol. 7, pp. 1022-1037, 1995
- B. S. Everitt,
An Introduction to Latent Variable Models,
London: Chapman and Hall, 1984
- U. Grenander,
Lectures in Pattern Theory I, II and III: Pattern Analysis,
Pattern Synthesis and Regular Structures,
Berlin: Springer-Verlag., Berlin, 1976-1981
- G.E. Hinton, P. Dayan, B. Frey, and R.M. Neal,
"The wake-sleep algorithm for self-organizing neural networks",
Science, vol. 268, pp. 1158-1160, 1995
- G.E. Hinton, and R.S. Zemel,
"Autoencoders, minimum description length and Helmholtz free energy",
In J.D. Cowan, G. Tesauro, and J. Alspector (editors),
Advances in Neural Information Processing Systems 6,
San Mateo, California: Morgan Kaufmann, pp. 3-10, 1994
- R.M. Neal, and G.E. Hinton,
"A new view of the EM algorithm that justifies incremental and
other variants",
submitted to Biometrika, 1994
- B.A. Olshausen, and D.J. Field,
"Sparse coding of natural images produces localized,
oriented, bandpass receptive fields",
Nature, 1996, in press
- P.N.R. Rao, and D.H. Ballard,
"Dynamic Model of Visual Memory predicts Neural Response
Properties in the Visual Cortex",
Technical report 95.4, Department of Computer Science,
Rochester, NY, 1995
- D.B. Rubin, and D.T. Thayer,
"EM algorithms for ML factor analysis",
Psychometrika, vol. 47, pp. 69-76, 1982
- R.S. Zemel,
"A Minimum Description Length Framework for Unsupervised Learning",
Ph.D. Thesis, Dept. of Computer Science, University of Toronto,
1994
back to the abstracts
P. Dayan
- S. P. Singh, and P. Dayan,
"Mean Squarred Error Curves in Temporal Difference Learning",
[available as pub/dayan/TDMSE/spsb.ps from ftp.ai.mit.edu]
- P. Dayan,
"The Convergence of TD-lambda for General lambda",
Machine Learning, vol. 8, no. 3/4, pp. 341-362, May 1992
- J. Tsitsiklis,
"Asynchronous Stochastic Approximation and Q-Learning",
Machine Learning, vol. 16, no. 3, pp. 185-202,
September 1994
- S. P. Singh, and R. S. Sutton,
"Reinforcement Learning with Replacing Eligibility Traces",
Machine Learning, 1996, to appear
- R. S. Sutton,
"Learning to Predict by the Methods of Temporal Differences",
Machine Learning, vol. 3, pp. 9-44, 1988
- T. Jaakkola, M. I. Jordan, and S. P. Singh,
"On the Convergence of Stochastic Iterative Dynamic Programming Algorithms",
Neural Computation, vol. 6, no. 6, pp. 1185-1201, 1994
back to the abstracts