USE OF GRADATED PATTERNS IN AN ASSOCIATIVE NEURAL MEMORY FOR INVARIANT PATTERN RECOGNITION

1994 ◽  
Vol 08 (02) ◽  
pp. 595-607
Author(s):  
KAZUKUNI KOBARA ◽  
TAIHO KANAOKA ◽  
YOSHIHIKO HAMAMOTO ◽  
SHINGO TOMITA ◽  
KOUKICHI MUNECHIKA
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Back Propagation ◽  
Point Of View ◽  
Network System ◽  
Back Propagation Algorithm ◽  
Error Back Propagation ◽  
Neural Network System ◽  
Feedback Error ◽  
Error Back Propagation Algorithm

Distortion invariant pattern recognition is an interesting problem from the biological and technological point of view. However, it has not yet been solved by neural networks in satisfactory way. This paper investigates an associative neural network system to improve the recalling accuracy for distortion patterns. On a perception type of neural network with feedback, error back-propagation algorithm and energy function are used for a learning process and a recalling process, respectively. By using gradated patterns as learning and unknown patterns, it is shown that the recalling accuracy becomes higher than using original pattern themselves.

Neural network-based hardware classifier using CORDIC algorithm

2020 ◽  
Vol 34 (15) ◽  
pp. 2050161
Author(s):  
Vipin Tiwari ◽  
Ashish Mishra
Keyword(s):  
Neural Network ◽  
Programming Languages ◽  
Back Propagation ◽  
Activation Function ◽  
Data Repository ◽  
Cordic Algorithm ◽  
Back Propagation Algorithm ◽  
Error Back Propagation ◽  
Benchmark Datasets ◽  
Error Back Propagation Algorithm

This paper designs a novel classification hardware framework based on neural network (NN). It utilizes COordinate Rotation DIgital Computer (CORDIC) algorithm to implement the activation function of NNs. The training was performed through software using an error back-propagation algorithm (EBPA) implemented in C++, then the final weights were loaded to the implemented hardware framework to perform classification. The hardware framework is developed in Xilinx 9.2i environment using VHDL as programming languages. Classification tests are performed on benchmark datasets obtained from UCI machine learning data repository. The results are compared with competitive classification approaches by considering the same datasets. Extensive analysis reveals that the proposed hardware framework provides more efficient results as compared to the existing classifiers.

scholarly journals Building robust neural networks using different loss functions

2021 ◽  
pp. 67-82
Author(s):  
Maria Sivak ◽  
◽  
Vladimir Timofeev ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Loss Function ◽  
Back Propagation ◽  
Loss Functions ◽  
Back Propagation Algorithm ◽  
Error Back Propagation ◽  
Propagation Algorithm ◽  
Error Back Propagation Algorithm ◽  
Parameter Values

The paper considers the problem of building robust neural networks using different robust loss functions. Applying such neural networks is reasonably when working with noisy data, and it can serve as an alternative to data preprocessing and to making neural network architecture more complex. In order to work adequately, the error back-propagation algorithm requires a loss function to be continuously or two-times differentiable. According to this requirement, two five robust loss functions were chosen (Andrews, Welsch, Huber, Ramsey and Fair). Using the above-mentioned functions in the error back-propagation algorithm instead of the quadratic one allows obtaining an entirely new class of neural networks. For investigating the properties of the built networks a number of computational experiments were carried out. Different values of outliers’ fraction and various numbers of epochs were considered. The first step included adjusting the obtained neural networks, which lead to choosing such values of internal loss function parameters that resulted in achieving the highest accuracy of a neural network. To determine the ranges of parameter values, a preliminary study was pursued. The results of the first stage allowed giving recommendations on choosing the best parameter values for each of the loss functions under study. The second stage dealt with comparing the investigated robust networks with each other and with the classical one. The analysis of the results shows that using the robust technique leads to a significant increase in neural network accuracy and in a learning rate.

Application of Artificial Neural Network for Prediction of Boride Layer Depth Obtained on XC38 Steel in Molten Salts

2015 ◽  
Vol 365 ◽  
pp. 194-199 ◽  
Author(s):  
Karim Rayane ◽  
Omar Allaoui
Keyword(s):  
Neural Network ◽  
Molten Salts ◽  
Good Accuracy ◽  
Back Propagation ◽  
Boride Layer ◽  
Network System ◽  
Back Propagation Algorithm ◽  
Layer Depth ◽  
Silicon Carbides ◽  
Neural Network System

This paper discusses an application of neural network system on the performance of boride layer thickness. Boriding treatment was carried out in three different molten salts consisting of borax (Na2B4O7) added to boron carbide (B4C), aluminum (Al) and silicon carbides (SiC). The substrate used in this study was XC38 steel. Borides layers involved in this work was obtained from a boriding treatment at the temperature range of 800-1050 °C with 50°C interval for 2, 4 and 6 h. A numerical experiment using normalized and binarized values was carried out, using a back-propagation algorithm in ANN. The modeling shows that for the three bath the depth of boride layer was predicted with good accuracy, with a highest performance of normalized values along experimental data range.

scholarly journals A Modified Neural Network system based on Morphological operations for detection of images with variation in Gray level intensity and facial expressions

2012 ◽  
pp. 56-61
Author(s):  
Pratibha Rani ◽  
Anshu Sirohi ◽  
Manish Kumar Singh
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Network System ◽  
Morphological Operations ◽  
Gray Level ◽  
Back Propagation Algorithm ◽  
Translation Invariant ◽  
The Neural Network ◽  
Neural Network System ◽  
Level Shifts

We introduce an algorithm based on the morphological shared-weight neural network. Which extract the features and then classify them. This type of network can work effectively, even if the gray level intensity and facial expression of the images are varied. The images are processed by a morphological shared weight neural network to detect and extract the features of face images. For the detection of the edges of the image we are using sobel operator. We are using back propagation algorithm for the purpose of learning and training of the neural network system. Being nonlinear and translation-invariant, the morphological operations can be used to create better generalization during face recognition. Feature extraction is performed on grayscale images using hit-miss transforms that are independent of gray-level shifts. The recognition efficiency of this modified network is about 98%.

scholarly journals A Pruning Neural Network Model in Credit Classification Analysis

2018 ◽  
Vol 2018 ◽  
pp. 1-22 ◽  
Author(s):  
Yajiao Tang ◽  
Junkai Ji ◽  
Shangce Gao ◽  
Hongwei Dai ◽  
Yang Yu ◽  
...  
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Dendritic Tree ◽  
Neural Model ◽  
Classification Problem ◽  
Dendritic Morphology ◽  
Superior Performance ◽  
Back Propagation Algorithm ◽  
Error Back Propagation ◽  
Error Back Propagation Algorithm

Nowadays, credit classification models are widely applied because they can help financial decision-makers to handle credit classification issues. Among them, artificial neural networks (ANNs) have been widely accepted as the convincing methods in the credit industry. In this paper, we propose a pruning neural network (PNN) and apply it to solve credit classification problem by adopting the well-known Australian and Japanese credit datasets. The model is inspired by synaptic nonlinearity of a dendritic tree in a biological neural model. And it is trained by an error back-propagation algorithm. The model is capable of realizing a neuronal pruning function by removing the superfluous synapses and useless dendrites and forms a tidy dendritic morphology at the end of learning. Furthermore, we utilize logic circuits (LCs) to simulate the dendritic structures successfully which makes PNN be implemented on the hardware effectively. The statistical results of our experiments have verified that PNN obtains superior performance in comparison with other classical algorithms in terms of accuracy and computational efficiency.

scholarly journals Enhancement of Shadow Region in an Image using Artificial Neural Network

2020 ◽  
Vol 9 (3) ◽  
pp. 3377-3382
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Back Propagation ◽  
Transformation Method ◽  
Back Propagation Algorithm ◽  
Important Data ◽  
Error Back Propagation ◽  
Proposed Model ◽  
Error Back Propagation Algorithm ◽  
Artificial Neural

Image captured in darker region increases complexities in processing and extracting vital information. Enhancement of such images helps us to retrieve important data and various tools are available for the same. Proposed system uses multi layer feed forward artificial neural network. Error Back Propagation algorithm is used in training process. Desired data is obtained using log transformation method. The proposed model is trained to enhance only shadow part of an image. The results shows enhancement in the darker region and is expected to improve more by changing different parameters in the above methodology.

Studying Fitting Effect by ANFIS in the Electrodialysis Process

2011 ◽  
Vol 268-270 ◽  
pp. 336-339
Author(s):  
Guo Lin Jing ◽  
Wen Ting Du ◽  
Quan Zhou ◽  
Song Tao Li
Keyword(s):  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Back Propagation ◽  
Fuzzy Model ◽  
Least Square Method ◽  
Least Square ◽  
Back Propagation Algorithm ◽  
Inference System ◽  
Error Back Propagation ◽  
Error Back Propagation Algorithm

Fuzzy system is known to predict model in the electrodialysis process. This paper aimed to study fitting effect by ANFIS in a laboratory scale ED cell. Separation percent of NaCl solution is mainly as a function of concentration, temperature, flow rate and voltage. Besides, ANFIS(Adaptive Neuro-Fuzzy Inference System) based on Sugeno fuzzy model, its structure was similar to neural network and could generate fuzzy rules automatically, using the error back propagation algorithm and least square method to adjust the parameters of fuzzy inference system. We obtained fitted values of separation percent by ANFIS. Separation percent from experiments compared with the fitted values of separation percent. The result is shown that the correlation coefficient is 0.988. Therefore, it is verified as a good performance in the electrodialysis process.

Sign in / Sign up

Export Citation Format

Share Document