NDLI: Neural network Bayes error estimation

Please wait, while we are loading the content...

2015 International Joint Conference on Neural Networks (IJCNN)

2014 International Joint Conference on Neural Networks (IJCNN)

The 2013 International Joint Conference on Neural Networks (IJCNN)

The 2012 International Joint Conference on Neural Networks (IJCNN)

The 2011 International Joint Conference on Neural Networks

The 2010 International Joint Conference on Neural Networks (IJCNN)

2009 International Joint Conference on Neural Networks

2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)

2007 International Joint Conference on Neural Networks

The 2006 IEEE International Joint Conference on Neural Network Proceedings

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.

2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)

Proceedings of the International Joint Conference on Neural Networks, 2003.

Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)

IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222)

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium

IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)

1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227)

Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94)

Volume 7 - 1994

Volume 6 - 1994

Volume 5 - 1994

Volume 4 - 1994

Volume 3 - 1994

Volume 2 - 1994

Volume 1 - 1994

Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94)

A high performance neural net simulation environment

A supercomputer for neural computation

High speed parallel hardware performance issues for neural network applications

An efficient multiprocessor mapping algorithm for the Kohonen feature map and its derivative models

Benchmarking of the CM-5 and the Cray machines with a very large backpropagation neural network

Reducing the number of multiplies in backpropagation

Accelerating the training of feedforward neural networks using generalized Hebbian rules for initializing the internal representations

The delta rule and learning for min-max neural networks

Bernoulli error measure approach to train feedforward artificial neural networks for classification problems

Optimizing locality of data representation in MLP networks

Estimating the mean and variance of the target probability distribution

Complexity of learning: the case of everyday neural networks

On the stability of symmetric adaptive decorrelation

Projection-based methods for stepsize adaptation and their application to the training of feedforward artificial neural networks

Case studies in the use of a hyperplane animator for neural network research

On the relative time complexities of standard and conjugate gradient backpropagation

A new approach in multilayer perceptron-forward propagation (FP)

A mapping from linear tree classifiers to neural net classifiers

Anti-Hebbian rule for faster backpropagation learning

GMDP: a novel unified neuron model for multilayer feedforward neural networks

Weight initialization of MLP classifiers using boundary-preserving patterns

A divide-and-conquer methodology for modular supervised neural network design

The SOLAR algorithm

Randomness in generalization ability: a source to improve it?

Regularization networks for approximating multi-valued functions: learning ambiguous input-output mappings from examples

Improving generalization performance by information minimization

Fault-tolerance inclusion in neural networks by a concurrent training algorithm

Enhanced back-propagation learning and its application to business evaluation

A criterion for training reference vectors and improved vector quantization

Parallel training of simple recurrent neural networks

Feedback-error learning scheme using recurrent neural networks for nonlinear dynamic systems

Method of digging tunnels horizontally into the error hypersurface to speed up training and to escape from local minima

Penalized learning as multiple object optimization

A learning algorithm for multi-layer perceptrons with hard-limiting threshold units

Constructive neural networks: some practical considerations

Constructively learning a near-minimal neural network architecture

Explicit synthesis of multilayer perceptrons using Walsh expansion

An incremental learning algorithm that optimizes network size and sample size in one trial

A neural net for blind separation of nonstationary signal sources

The fractal geometry of backpropagation

Structure training of neural networks

The second derivative of a recurrent network

Analysis of input vector space for speeding up learning in feedforward neural networks

A first order adaptive learning rate algorithm for backpropagation networks

How to "secure" the decisions of a NN classifier

Structure of learning in the complex numbered back-propagation network

A structural learning by adding independent noises to hidden units

Study on effect of deterministic learning sequencer

An efficient constrained learning algorithm for optimal linear separability of the internal representations

Transformation of back-propagation networks in multiresolution learning

Delta training strategies

Wavelet neural networks are asymptotically optimal approximators for functions of one variable

Neural network Bayes error estimation

Comparison of four learning algorithms for multilayer perceptron with FIR synapses

Multisets modeling learning: an unified theory for supervised and unsupervised learning

A note on the estimation of the generalization error and the prevention of overfitting [machine learning]

How practical are VC dimension bounds? [learning from examples]

Modifying training algorithms for improved fault tolerance

Adaptive gain networks

Introducing invariance: a principled approach to weight sharing

A large scale neural network with nonlinear synapses

Structural learning and its applications to rule extraction

A study on the partitioning capabilities of two-layer neural networks

Network complexity and learning efficiency of constructive learning algorithms

On-line stable nonlinear modelling by structurally adaptive neural nets

Simple heuristic methods for input parameters' estimation in neural networks

A note on backpropagation, projection learning, and feedback in neural systems

The manifold backpropagation algorithm

MMI training of minimum complexity adaptive nearest neighbor classifiers

RBF and CBF neural network learning procedures

Application of Prony signal analysis to recurrent neural networks

Maximizing fault tolerance in multilayer neural networks

Preprocessing of training set for backpropagation algorithm: histogram equalization

Optimization of activation functions in multilayer neural network applied to pattern classification

Reinforcement learning using a recurrent neural network

A multi temporal trainable delay neural network

Dynamic adaptation of the error surface for the acceleration of the training of neural networks

Bifurcations in nonlinear networks initialized with linear network weight solutions

A neural network model with compensating inputs

An automated approach for selecting the learning rate and momentum in backpropagation networks

NN-learning with backpropagation and adaptive filter techniques

An update function that speeds up backpropagation learning

Experimental analysis of the random memory space

Directed product term selection in Sigma-Pi networks

An efficient training algorithm for multilayer neural networks by homotopy continuation method

An implementation and evaluation of the ART1 neural network for pattern recognition

Factors influencing the choice of a learning rate for a backpropagation neural network

Scaling properties of on-line learning with momentum

A robust approach to supervised learning in neural network

A training approach based on linear separability analysis for layered perceptrons

Feedforward neural networks to learn drawing lines

Training hard-limiting neurons using back-propagation algorithm by updating steepness factors

Feature induction by backpropagation

On modifying the weights in a modular recurrent connectionist system

An efficient algorithm for clustering data and best model selection using AIC

Geometrical initialization, parametrization and control of multilayer perceptrons: application to function approximation

A choosing method of training sets which prevent over-learning

Two adaptive stepsize rules for gradient descent and their application to the training of feedforward artificial neural networks

Sequential classification by perceptrons and application to net pruning of multilayer perceptron

Are modified back-propagation algorithms worth the effort?

A novel approach to fast learning: smart neural nets

Speed up the learning process of feedforward neural networks

A fast and robust pattern recognition using a new algorithm for training feed-forward neural networks

Generalization and C-information

Improving generalization performance by controlling /spl alpha/-information

An analysis of weight decay as a methodology of reducing three-layer feedforward artificial neural networks for classification problems

Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan)

[Proceedings 1992] IJCNN International Joint Conference on Neural Networks

[Proceedings] 1991 IEEE International Joint Conference on Neural Networks

IJCNN-91-Seattle International Joint Conference on Neural Networks

1990 IJCNN International Joint Conference on Neural Networks

International 1989 Joint Conference on Neural Networks

Neural network Bayes error estimation

Content Provider	IEEE Xplore Digital Library
Author	Martin, C.E. Rogers, S.K. Ruck, D.W.
Copyright Year	1994
Description	Author affiliation: Dept. of Electr. & Comput. Eng., Wright Res. & Dev. Center, Wright-Patterson AFB, OH, USA (Martin, C.E.; Rogers, S.K.; Ruck, D.W.)
Abstract	A neural network approach to obtaining upper and lower bounds on the Bayes error rate for pattern recognition problems is presented. The approach is developed using the key concept of resubstitution and leave-one-out testing from conventional nonparametric error estimation techniques. The neural network approach is evaluated by applying it to several eight-dimensional, two-class "toy" problems, where the Bayes error rate is known. The upper bound of the Bayes error rate is reliably found for problems with complex decision boundary surfaces. Alternative testing approaches are suggested for reducing the difference between the bounds and the true Bayes rate.
Starting Page	305
Ending Page	308
File Size	371216
Page Count	4
File Format	PDF
ISBN	078031901X
DOI	10.1109/ICNN.1994.374180
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	1994-06-28
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Neural networks Error analysis Pattern recognition Upper bound Benchmark testing Density functional theory Density measurement Probability density function Estimation theory Multilayer perceptrons
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in