Upper bound of the expected training error of neural network regression for a Gaussian noise sequence

Hagiwara, Katsuyuki; Hayasaka, Taichi; Toda, Naohiro; Usui, Shiro; Kuno, Kazuhiro

doi:10.1016/s0893-6080(01)00122-8

Cited by 29 publications

(32 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The network is trained with Matlab-function traingda of the backpropagation algorithm, whereby 2 replicas of the pure symbol alphabet and 4 noised symbol alphabets are passed for 10 times. Practicing, it is sufficient to vary that number from 10 up to 120, as with neuron 10 q < the neural network is trained too slow (Figure 1), and with neuron 120 q > the neural network mean recognition error rate (Figure 2) becomes greater than the error rate for the network, trained without noise (Hagiwara, Hayasaka, Toda, Usui, & Kuno, 2001). It is seen from Figures 1 and 2 = , leading to 49 neurons in the hidden layer.…”

Section: Setting Neurons Into the Hidden Layer For A Practical Casementioning

confidence: 98%

Setting the Hidden Layer Neuron Number in Feedforward Neural Network for an Image Recognition Problem under Gaussian Noise of Distortion

Romanuke¹

2013

CIS

View full text Add to dashboard Cite

There is considered an image recognition problem, defined for the single hidden layer perceptron, fed with 5-by-7 monochrome images on its input under Gaussian noise of their distortion. In this neural network the hidden layer neuron number should be set optimally to maximize its productivity. For minimizing traintime duration and recognition error rate both simultaneously there are suggested two ways of solving the corresponding two-objective minimization problem. One of them deals with equilibrium conception, and the other takes Bernoulli criterion for getting the single minimization problem.

show abstract

Section: Setting Neurons Into the Hidden Layer For A Practical Casementioning

confidence: 98%

Setting the Hidden Layer Neuron Number in Feedforward Neural Network for an Image Recognition Problem under Gaussian Noise of Distortion

Romanuke¹

2013

CIS

View full text Add to dashboard Cite

show abstract

“…Let the usefulness of 2LP (16) during the training be measured with its performance function "mse" according to the sum of squared errors [8], [9], [22], [23]. Finally, having preset the minimum performance gradient to 6 10  , let the number of epochs be 5000 in order to prevent long-dragging convergence of TP and to shorten the ultimate TP period for each pass.…”

Section: Description Of 2lp (6) Configuration For M6080ismentioning

confidence: 99%

“…However, yielding to PSTSSD 0.08 r  on average (see Fig. 2 Before verification, the best one of 100 2LPs (30) must be trained further until its performance becomes unimprovable [5], [8], [28]. The best 2LP (30) performs at an average CEP, which is 9.31 %.…”

Section: Models Of Stsm6080i and Stsm6080i Ndpdmentioning

confidence: 99%

Classifying Scaled-Turned-Shifted Objects with Optimal Pixel-to-Scale-Turn-Shift Standard Deviations Ratio in Training 2-Layer Perceptron on Scaled-Turned-Shifted 4800-Featured Objects under Normally Distributed Feature Distortion

Romanuke

2017

Electrical, Control and Communication Engineering

View full text Add to dashboard Cite

-The problem of classifying diversely distorted objects is considered. The classifier is a 2-layer perceptron capable of classifying greater amounts of objects in a unit of time. This is an advantage of the 2-layer perceptron over more complex neural networks like the neocognitron, the convolutional neural network, and the deep learning neural networks. Distortion types are scaling, turning, and shifting. The object model is a monochrome 60 × 80 image of the enlarged English alphabet capital letter. Consequently, there are 26 classes of 4800-featured objects. Training sets have a parameter, which is the ratio of the pixel-to-scale-turn-shift standard deviations, which allows controlling normally distributed feature distortion. An optimal ratio is found, at which the performance of the 2-layer perceptron is still unsatisfactory. Then, the best classifier is further trained with additional 438 passes of training sets by increasing the training smoothness tenfold. This aids in decreasing the ultimate classification error percentage from 35.23 % down to 12.92 %. However, the expected practicable distortions are smaller, so the percentage corresponding to them becomes just 1.64 %, which means that only one object out of 61 is misclassified. Such a solution scheme is directly applied to other classification problems, where the number of features is a thousand or a few thousands by a few tens of classes.

show abstract

“…By the way, testing sets differ from training sets because it is sufficient to evaluate CEP only at the SDI maximum [15], [23], [28], [29]. …”

Section: Formalisation Of the 2lp Classifiermentioning

confidence: 99%

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Romanuke

2015

Information Technology and Management Science

View full text Add to dashboard Cite

-The research is focused on optimising two-layer perceptron for generalised scaled object classification problem. The optimisation criterion is minimisation of inaccuracy. The inaccuracy depends on training parameters and hidden layer neuron number. After its statistics is accumulated, minimisation is executed by a numerical search. Perceptron is optimised additionally by extra training. As it is done, the classification error percentage does not exceed 3 % in case of the worst scale distortion.

show abstract

Upper bound of the expected training error of neural network regression for a Gaussian noise sequence

Cited by 29 publications

References 14 publications

Setting the Hidden Layer Neuron Number in Feedforward Neural Network for an Image Recognition Problem under Gaussian Noise of Distortion

Setting the Hidden Layer Neuron Number in Feedforward Neural Network for an Image Recognition Problem under Gaussian Noise of Distortion

Classifying Scaled-Turned-Shifted Objects with Optimal Pixel-to-Scale-Turn-Shift Standard Deviations Ratio in Training 2-Layer Perceptron on Scaled-Turned-Shifted 4800-Featured Objects under Normally Distributed Feature Distortion

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Contact Info

Product

Resources

About