References

1

L. Lönnblad, C. Peterson and T. Rögnvaldsson, ``Pattern Recognition in High Energy Physics with Artificial Neural Networks'', Comput. Phys. Commun. 70, 167 (1992).

2

L. Lönnblad, C. Peterson and T. Rögnvaldsson, "Using Neural Networks to Identify Jets", Nucl. Phys. B 349, 675 (1991).

3

L. Lönnblad, C. Peterson and T. Rögnvaldsson, "Finding Gluon Jets with a Neural trigger", Phys. Rev. Lett. 65, 1321 (1990).

4

L. Lönnblad, C. Peterson, H. Pi and T. Rögnvaldsson, ``Self-organizing Networks for Extracting Jet Features'', Comput. Phys. Commun. 67, 193 (1991).

5

D. E. Rumelhart, G. E. Hinton and R. J. Williams, ``Learning Internal Representations by Error Propagation'', in D. E. Rumelhart and J. L. McClelland (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition (Vol. 1), MIT Press (1986).

6

T. Rögnvaldsson, ``On Langevin Updating in Multilayer Perceptrons'', Lund Preprint LU TP 93-13 (to appear in Neural Comput.) (1994).

7

E. M. Johansson, F. U. Dowla and D. M. Goodman, ``Backpropagation Learning for Multilayer Feed-forward Neural Networks using the Conjugate Gradient Method'', Int. J. Neur. Syst. 2, 291 (1992).

8

M. F. Mø ller, ``A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning'', Neural Networks 6, 525 (1993).

9

S. E. Fahlman, ``An Empirical Study of Learning Speed in Back-propagation Networks'', Carnegie-Mellon Computer Science Rpt. CMU-CS-88-162 (1988).

10

M. Riedmiller and H. Braun, ``A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm'', Proc. ICNN, San Fransisco (1993).

11

B. Denby, "Neural Networks and Cellular Automata in Experimental High Energy Physics", Comput. Phys. Commun. 49, 429 (1988).

12

C. Peterson, "Track Finding with Neural Networks", Nucl. Instrum. Methods A279, 537 (1989).

13

M. Gyulassy and H. Harlander, ``Elastic Tracking and Neural Network Algorithms for Complex Pattern Recognition'', Comput. Phys. Commun. 66, 31 (1991).

14

A. Yuille, K. Honda and C. Peterson, ``Particle Tracking by Deformable Templates'', Proceedings of 1991 IEEE INNS International Joint Conference on Neural Networks, Vol. 1, pp 7-12, Seattle, WA (July 1991)

15

M. Ohlsson, C. Peterson and A. Yuille, ``Track Finding with Deformable Templates -- The Elastic Arms Approach'', Comput. Phys. Commun. 71, 77 (1992).

16

M. Ohlsson, ''Extensions and Explorations of the Elastic Arms Algorithm'', Comput. Phys. Commun. 77, 19 (1992).

17

C. Peterson and E. Hartman, ``Explorations of the Mean Field Theory Learning Algorithm'', Neural Networks 2, 475 (1989).

18

S. Saarinen, R. Bramley and G. Cybenko, ``Ill-conditioning in Neural Network Training Problem'', SIAM J. Sci. Comp. 14, 693 (1993).

19

R. Battiti, ``First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method'', Neural Comput. 4, 141 (1992).

20

A. C. Veitch and G. Holmes, ``A Modified Quickprop Algorithm'', Neural Comput. 3, 310 (1991).

21

R. Jacobs, ``Increased Rates of Convergence Through Learning Rate Adaption'', Neural Networks 1, 295 (1988).

22

T. Tollenaere, ``SuperSAB: Fast Adaptive Backpropagation with Good Scaling Properties'', Neural Networks 3, 561 (1990).

23

W. H. Press, B. P. Flannery, S. A. Teukolsky and W. T. Vetterling, Numerical Recipes, Cambridge Univ. Press, Cambridge UK (1986).

24

M. D. Richard and R. P. Lippmann, ``Neural Network Classifiers Estimate Bayesian a posteriori Probabilities'', Neural Comput. 3, 461 (1991).

25

S. Geman, E. Bienenstock and R. Doursat, ``Neural Networks and the Bias/Variance Dilemma'', Neural Comput. 4, 1 (1992).

26

K. H. Becks, F. Block, J. Drees, P. Langefeld and F. Seidel, ``B-quark Tagging using Neural Networks and Multivariate Statistical Methods -- A Comparison of Both Techniques'', Nucl. Instrum. Methods A329, 501 (1993).

27

J. Proriol et. al., ``Tagging B Quark Events in Aleph with Neural Networks'', Proceedings of Workshop in Neural Networks: From Biology to High Energy Physics, June 1991, Elba, Italy, eds. O. Benhar, C. Bosio, P. Del Giudice and E. Tabet, ETS EDITRICE (Pisa 1991).

28

R. Belloti et al., ``A Comparison Between a Neural Network and the Likelihood Method to Evaluate the Performance of a Transition Radiation Detector'', Comput. Phys. Commun. 78, 17 (1993).

29

G. Stimpfl-Abele, ``Recognition of Charged Tracks with Neural Network Techniques'', Comput. Phys. Commun. 67, 183 (1991).

30

G. Stimpfl-Abele and P. Yepes, ``Higgs Search and Neural Net Analysis'', Comput. Phys. Commun. 78, 1 (1993).

31

W. S. Babbage and L. F. Thompson, ``The Use of Neural Networks in Discrimination'', Nucl. Instrum. Methods A330, 482 (1993).

32

J. F. Kreider and J. S. Haberl, ``Predicting Hourly Building Energy Usage: The Great Energy Predictor Shootout -- Overview and Discussion of Results'', to appear in 1994 ASHRAE Trans. 100, part 2 (1994).

33

B. D. Ripley, ``Flexible Non-linear Approaches to Classification'', in V. Cherkassky, J. H. Friedman and H. Wechsler (eds.) From Statistics to Neural Networks NATO ASI Proceedings, subseries F, Springer-Verlag (1993).

34

R. Duda and P. E. Hart, Pattern Classification and Scene Analysis, Wiley: New York (1973).

35

A. Murray, ``Multilayer Perceptron Learning Optimized for On-chip Implementation: A Noise Robust System'', Neural Comput. 4, 366 (1992).

36

A. R. Barron, ``Approximation and Estimation Bounds for Artificial Neural Networks'', Machine Learning 14, 115 (1994).

37

T. Kohonen, Self-organization and Associative Memory 3rd ed., Springer-Verlag, Heidelberg (1990).

38

T. Rögnvaldsson, ``Pattern Discrimination Using Feedforward Networks: A Benchmark Study of Scaling Behavior'', Neural Comput. 5, 483 (1993).

39

J. Proriol, ``Multi-modular Networks for the Classification of Hadronic Events'', to appear in Nucl. Instrum. Methods A, (1994).

40

S. E. Fahlman and C. Lebiere, ``The Cascade Correlation Learning Architecture'', Carnegie Mellon Computer Science Rpt. CMU-CS-90-100 (1990).

41

E. Hartman and J. D. Keeler, ``Predicting the Future: Advantages of Semilocal Units'', Neural Comput. 3, 566 (1991).

42

J. Moody and C. J. Darken, ``Fast Learning in Networks of Locally-tuned Processing Units'', Neural Comput. 1, 281 (1989).

43

L. Lönnblad, C. Peterson and T. Rögnvaldsson, ``Mass Reconstruction with a Neural Network'', Phys. Lett. B278, 181 (1992).

44

J. MacQueen, ``Some Methods for Classification and Analysis of Multivariate Observations'', Proc. 5th Berkeley Symposium Math. Stat. and Prob., J. M. LeCam and J. Neyman (eds.), Univ. of California Press, Berkeley (1967).

45

T. M. Martinetz, H. Ritter and K. J. Schulten, ``Three-dimensional Neural Net for Learning Visuomotor-Coordination of a Robot Arm'', IEEE Trans. Neur. Netw. 1, 131 (1989).

46

T. M. Martinetz, S. G. Berkovich and K. J.Schulten, ``Neural-Gas Network for Vector Quantization and its Application to Time-Series Prediction'', IEEE Trans. Neur. Netw. 4, 558 (1993).

47

L. Breiman, J. H. Friedman, R. A. Olsen and C. J. Stone, Classification and Regression Trees, Wadsworth, Monterey CA (1984).

48

J. H. Friedman, ``Multivariate Adaptive Regression Splines'', Ann. of Stat. 19, 1 (1991).

49

M. Ohlsson, C. Peterson, H. Pi, T.Rögnvaldsson and B. Söderberg, ``Predicting Utility Loads with Artificial Neural Networks -- Methods and Results from the Great Energy Predictor Shootout'', Lund Preprint LU TP 93-24 (to appear in 1994 ASHRAE Trans. 100, part2), (1994).

50

K. Fukunaga, Introduction to Statistical Pattern Recognition, 2:nd ed., Academic Press Inc., San Diego CA (1990).

51

A. A. Chilingarian and G. Z. Zazian, ``A Bootstrap Method of Distribution Mixture Proportion Determination'', Pat. Rec. Lett. 11, 781 (1990).

52

J. Utans and J. Moody, ``Selecting Neural Network Architecture via the Prediction Risk: Application to Corporate Bond Rating Prediction'', Proc. First Intl. Conf. on AI Appl. on Wall Street, IEEE Press, Los Alamitos CA (1991).

53

J. Moody, ``The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems'', Adv. in Neur. Inf. Proc. Syst. 4, Morgan Kaufmann, San Mateo CA (1992).

54

N. Murata, S. Yoshizawa and S. Amari, ``Network Information Criterion -- Determining the Number of Hidden Units for an Artificial Neural Network Model'', to appear in IEEE Trans. Neur. Netw., (1993).

55

G. Cybenko, ``Approximation by Superposition of a Sigmoidal Function'', Math. Control Signals Systems 2, 303 (1989).

56

H. H. Szu, X. Yang, B. A. Telfer, Y. Sheng, ``Neural Network and Wavelet Transform for Scale-invariant Data Classification'', Phys. Rev. E 48, 48 (1993).

57

S. J. Nowlan and G. E. Hinton, ``Simplifying Neural Networks by Soft Weight-Sharing'', Neural Comput. 4, 473 (1992).

58

J. M. J. Murre, ``Neurosimulators'', review to appear in M. A. Arbib (ed.) Handbook of Brain Research and Neural Networks, MIT Press (1995).

59

W. Schiffmann, M. Joost and R. Werner, ``Comparison of Optimized Backpropagation Algorithms'', Proc. ESANN 93 Brussels (1993).

60

D. Buskulic, et. al., ``Measurement of the Ratio using Event Shape Variables'', Phys. Lett. B313, 549 (1993).

61

H. Pi and C. Peterson, ``Finding the Embedding Dimension and Variable Dependencies in Time Series'', Lund Preprint LU TP 93-4 (to appear in Neural Comput.) (1994).

62

A. A. Chilingarian, ``Statistical Decisions under Nonparametric a Priori Information'', Comput. Phys. Commun. 54, 381 (1989).

63

A. Weigend, B. Huberman and D. Rumelhart, ``Predicting Sunspots and Exchange Rates with Connectionist Networks'', Nonlin. Modeling and Forecasting, Addison-Wesley (1991).

64

M. C. Mozer and P. Smolensky, ``Using Relevance to Reduce Network Size Automatically'', Connection Science 1, 3 (1989).

65

Y. Le Cun, J. S. Denker and S. A. Solla, ``Optimal Brain Damage'', Neur. Inform. Proc. Systems 2, 598 (1990).

66

B. Hassibi and D. G. Stork, ``Second Order Derivatives for Network Pruning: Optimal Brain Surgeon'', Neur. Inform. Proc. Systems 5, 164 (1993).

67

L. F. A. Wessels and E. Barnard, ``Avoiding False Local Minima by Proper Initialization of Connections'', IEEE Trans. Neur. Netw. 3, 899 (1992).

68

T. Denoeux and R. Lengellé, ``Initializing Back Propagation Networks with Prototypes'', Neural Networks 6, 351 (1993).

69

T. P. Vogl et al., ``Accelerating the Convergence of the Back-Propagation Method'', Biol. Cybern. 59, 257 (1988).

70

C. Darken, J. Chang and J. Moody, ``Learning Rate Schedules for Faster Stochastic Gradient Descent'', Proc. 1992 IEEE Worksh. Neur. Netw. Signal Processing, 3 (1992).

71

Y. LeCun, P. Y. Simard and B. Pearlmutter, ``Automatic Learning Rate Maximization by On-Line Estimation of the Hessian's Eigenvectors'', Proc. Neur. Inf. Proc. Syst. 5, 156 (1993).

72

T. M. Heskes and B. Kappen, ``Learning-parameter Adjustment in Neural Networks'', Phys. Rev. A 45, 8885 (1992).

73

F. James, ``MINUIT'', Comput. Phys. Commun. 10, 343 (1975)

74

O. Catoni, ``Rough Large Deviation Estimates for Simulated Annealing Applications to Exponential Schedules'', Ann. of Probability 20, 1109 (1992).

75

F. James, ``A Review of Pseudorandom Number Generators'', Comput. Phys. Commun. 60, 329 (1990).