scholarly journals An Innovative Way to Measure the Quality of a Neural Network Without the Use of a Test Set

2001 ◽  
Vol 5 (1) ◽  
pp. 31-36 ◽  
Author(s):  
Giovanni Pilato ◽  
◽  
Filippo Sorbello ◽  
Giorgio Vassallo
Keyword(s):  
Neural Network ◽  
Computational Cost ◽  
Experimental Results ◽  
Output Function ◽  
Quality Factors ◽  
Generalization Capability ◽  
Training Set ◽  
Test Set ◽  
Network Output

In this paper, three quality factors are introduced in order to measure the quality of a neural network. Each factor deals with a particular feature of quality: the ability of the network in learning training set samples; generalization capability related to the gradient, in the nearby of the training patterns, of the network output function; the computational cost of the architecture during the production phase, related to the number of connections between neural units. The validity of the proposed solution has been tested using three well-known benchmarks. Experimental results show that quality factors introduced in this paper can be a valid alternative to the test set method.

scholarly journals Order-Free Learning Alleviating Exposure Bias in Multi-Label Classification

2020 ◽  
Vol 34 (04) ◽  
pp. 6038-6045
Author(s):  
Che-Ping Tsai ◽  
Hung-Yi Lee
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Experimental Results ◽  
Prediction Problem ◽  
Generalization Capability ◽  
Training Set ◽  
Large Margin ◽  
Sequence Prediction ◽  
Benchmark Datasets ◽  
New Framework

Multi-label classification (MLC) assigns multiple labels to each sample. Prior studies show that MLC can be transformed to a sequence prediction problem with a recurrent neural network (RNN) decoder to model the label dependency. However, training a RNN decoder requires a predefined order of labels, which is not directly available in the MLC specification. Besides, RNN thus trained tends to overfit the label combinations in the training set and have difficulty generating unseen label sequences. In this paper, we propose a new framework for MLC which does not rely on a predefined label order and thus alleviates exposure bias. The experimental results on three multi-label classification benchmark datasets show that our method outperforms competitive baselines by a large margin. We also find the proposed approach has a higher probability of generating label combinations not seen during training than the baseline models. The result shows that the proposed approach has better generalization capability.

scholarly journals Radial Basis Function Artificial Neural Network for the Investigation of Thyroid Cytological Lesions

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Christos Fragopoulos ◽  
Abraham Pouliakis ◽  
Christos Meristoudis ◽  
Emmanouil Mastorakis ◽  
Niki Margari ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Radial Basis Function ◽  
Basis Function ◽  
Histological Evaluation ◽  
Image Analysis System ◽  
Training Set ◽  
Test Set ◽  
Radial Basis ◽  
Artificial Neural

Objective. This study investigates the potential of an artificial intelligence (AI) methodology, the radial basis function (RBF) artificial neural network (ANN), in the evaluation of thyroid lesions. Study Design. The study was performed on 447 patients who had both cytological and histological evaluation in agreement. Cytological specimens were prepared using liquid-based cytology, and the histological result was based on subsequent surgical samples. Each specimen was digitized; on these images, nuclear morphology features were measured by the use of an image analysis system. The extracted measurements (41,324 nuclei) were separated into two sets: the training set that was used to create the RBF ANN and the test set that was used to evaluate the RBF performance. The system aimed to predict the histological status as benign or malignant. Results. The RBF ANN obtained in the training set has sensitivity 82.5%, specificity 94.6%, and overall accuracy 90.3%, while in the test set, these indices were 81.4%, 90.0%, and 86.9%, respectively. Algorithm was used to classify patients on the basis of the RBF ANN, the overall sensitivity was 95.0%, the specificity was 95.5%, and no statistically significant difference was observed. Conclusion. AI techniques and especially ANNs, only in the recent years, have been studied extensively. The proposed approach is promising to avoid misdiagnoses and assists the everyday practice of the cytopathology. The major drawback in this approach is the automation of a procedure to accurately detect and measure cell nuclei from the digitized images.

scholarly journals Obtaining High-Quality Label by Distinguishing between Easy and Hard Items in Crowdsourcing

2017 ◽  
Author(s):  
Wei Wang ◽  
Xiang-Yu Guo ◽  
Shao-Yuan Li ◽  
Yuan Jiang ◽  
Zhi-Hua Zhou
Keyword(s):  
Large Scale ◽  
Experimental Results ◽  
Training Set ◽  
High Quality ◽  
Quality Label ◽  
Large Scale Data ◽  
Voluntary Workers ◽  
Scale Data

Crowdsourcing systems make it possible to hire voluntary workers to label large-scale data by offering them small monetary payments. Usually, the taskmaster requires to collect high-quality labels, while the quality of labels obtained from the crowd may not satisfy this requirement. In this paper, we study the problem of obtaining high-quality labels from the crowd and present an approach of learning the difficulty of items in crowdsourcing, in which we construct a small training set of items with estimated difficulty and then learn a model to predict the difficulty of future items. With the predicted difficulty, we can distinguish between easy and hard items to obtain high-quality labels. For easy items, the quality of their labels inferred from the crowd could be high enough to satisfy the requirement; while for hard items, the crowd could not provide high-quality labels, it is better to choose a more knowledgable crowd or employ specialized workers to label them. The experimental results demonstrate that the proposed approach by learning to distinguish between easy and hard items can significantly improve the label quality.

A SEGMENTATION-FREE RECOGNITION OF HANDWRITTEN TOUCHING NUMERAL PAIRS USING MODULAR NEURAL NETWORK

2001 ◽  
Vol 15 (06) ◽  
pp. 949-966 ◽  
Author(s):  
SOON-MAN CHOI ◽  
Il-SEOK OH
Keyword(s):  
Neural Network ◽  
Conventional Approach ◽  
Experimental Results ◽  
Large Set ◽  
Training Set ◽  
Modular Neural Network ◽  
Large Size

The conventional approach to the recognition of handwritten touching numeral pairs uses a process with two steps; splitting the touching numerals and recognizing individual numerals. It shows a limitation mainly due to a large variation in touching styles between two numerals. In this paper, we adopt the segmentation-free approach, which regards a touching numeral pair as an atomic pattern. Two important issues are raised, i.e. solving the large-set classification and constructing a large-size training set. For the 100-class classification, we use a modular neural network which consists of 100 separate subnetworks. We construct the training set with a balance among 100 classes and using a sufficient amount by extracting actual samples from a numeral database and synthesizing samples with a scheme of forcing two numerals to touch. The experimental results show a promising performance.

Investigation of Neural-Network-Based Inverse Kinematics for a 6-DOF Serial Manipulator With Non-Spherical Wrist

2018 ◽  
Author(s):  
Benjamin E. Hargis ◽  
Wesley A. Demirjian ◽  
Matthew W. Powelson ◽  
Stephen L. Canfield
Keyword(s):  
Neural Network ◽  
Inverse Kinematics ◽  
Computational Time ◽  
Robot Arm ◽  
Training Set ◽  
Test Set ◽  
Network Training ◽  
Inverse Kinematics Problem ◽  
Spherical Wrist ◽  
Artificial Neural Network Ann

This study proposes using an Artificial Neural Network (ANN) to train a 6-DOF serial manipulator with a non-spherical wrist to solve the inverse kinematics problem. In this approach, an ANN has been trained to determine the configuration parameters of a serial manipulator that correspond to the position and pose of its end effector. The network was modeled after the AUBO-i5 robot arm, and the experimental results have shown the ability to achieve millimeter accuracy in tool space position with significantly reduced computational time relative to an iterative kinematic solution when applied to a subset of the workspace. Furthermore, a separate investigation was conducted to quantify the relationship between training example density, training set error, and test set error. Testing indicates that, for a given network, sufficient example point density may be approximated by comparing the training set error with test set error. The neural network training was performed using the MATLAB Neural Network Toolbox.

scholarly journals A Double-Branch Surface Detection System for Armatures in Vibration Motors with Miniature Volume Based on ResNet-101 and FPN

Sensors ◽  
2020 ◽  
Vol 20 (8) ◽  
pp. 2360
Author(s):  
Tao Feng ◽  
Jiange Liu ◽  
Xia Fang ◽  
Jie Wang ◽  
Libin Zhou
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Complete System ◽  
Detection System ◽  
Discrimination Performance ◽  
Training Method ◽  
Production Lines ◽  
Training Set ◽  
Test Set

In this paper, a complete system based on computer vision and deep learning is proposed for surface inspection of the armatures in a vibration motor with miniature volume. A device for imaging and positioning was designed in order to obtain the images of the surface of the armatures. The images obtained by the device were divided into a training set and a test set. With continuous experimental exploration and improvement, the most efficient deep-network model was designed. The results show that the model leads to high accuracy on both the training set and the test set. In addition, we proposed a training method to make the network designed by us perform better. To guarantee the quality of the motor, a double-branch discrimination mechanism was also proposed. In order to verify the reliability of the system, experimental verification was conducted on the production line, and a satisfactory discrimination performance was reached. The results indicate that the proposed detection system for the armatures based on computer vision and deep learning is stable and reliable for armature production lines.

scholarly journals Emotion Recognition using Convolutional Neural Network in Virtual Meeting Environment

2021 ◽  
Vol 13 (1) ◽  
pp. 30-38
Author(s):  
Nabila Husna Shabrina ◽  
Julando Omar ◽  
Akmal Nusa Bhakti ◽  
Axel Patria
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Emotion Recognition ◽  
Recognition System ◽  
Cascade Classifier ◽  
Training Process ◽  
Training Set ◽  
Test Set ◽  
Virtual Meeting ◽  
Haar Cascade

This study is done in order to propose an Emotion Recognition System that uses Convolutional Neural Network in a Virtual Meeting Environment to detect non-verbal feedback that emerge when communicating. This study starts with the training process of the CNN model with version 2.3.0 of tensorflow-gpu library, along with FER-2013 dataset, where only 80% of the data is used as the training set, and the other 20% is used as the test set. The model is trained for 430 epochs that results in 73.86% rate of accuracy with a loss of 1.42. In the classification process, a Haar-Cascade Classifier algorithm is used to detect faces within an image that has been inputted using OpenCV. Next the already developed model is used to predict the image that has been pre-processed. Based on the results shown, it can be concluded that the study has provided satisfactory results and is expected to help in understanding non-verbal input given when communicating and among other various things.

scholarly journals Emotion Recognition of Chinese Paintings at the Thirteenth National Exhibition of Fines Arts in China Based on Advanced Affective Computing

2021 ◽  
Vol 12 ◽  
Author(s):  
Jing Li ◽  
Dongliang Chen ◽  
Ning Yu ◽  
Ziping Zhao ◽  
Zhihan Lv
Keyword(s):  
Neural Network ◽  
Emotion Recognition ◽  
Affective Computing ◽  
Chinese Painting ◽  
Training Set ◽  
Chi Square ◽  
Test Set ◽  
Chi Square Test ◽  
Multimodal Emotion Recognition ◽  
Traditional Chinese Painting

Today, with the rapid development of economic level, people’s esthetic requirements are also rising, they have a deeper emotional understanding of art, and the voice of their traditional art and culture is becoming higher. The study expects to explore the performance of advanced affective computing in the recognition and analysis of emotional features of Chinese paintings at the 13th National Exhibition of Fines Arts. Aiming at the problem of “semantic gap” in the emotion recognition task of images such as traditional Chinese painting, the study selects the AlexNet algorithm based on convolutional neural network (CNN), and further improves the AlexNet algorithm. Meanwhile, the study adds chi square test to solve the problems of data redundancy and noise in various modes such as Chinese painting. Moreover, the study designs a multimodal emotion recognition model of Chinese painting based on improved AlexNet neural network and chi square test. Finally, the performance of the model is verified by simulation with Chinese painting in the 13th National Exhibition of Fines Arts as the data source. The proposed algorithm is compared with Long Short-Term Memory (LSTM), CNN, Recurrent Neural Network (RNN), AlexNet, and Deep Neural Network (DNN) algorithms from the training set and test set, respectively, The emotion recognition accuracy of the proposed algorithm reaches 92.23 and 97.11% in the training set and test set, respectively, the training time is stable at about 54.97 s, and the test time is stable at about 23.74 s. In addition, the analysis of the acceleration efficiency of each algorithm shows that the improved AlexNet algorithm is suitable for processing a large amount of brain image data, and the acceleration ratio is also higher than other algorithms. And the efficiency in the test set scenario is slightly better than that in the training set scenario. On the premise of ensuring the error, the multimodal emotion recognition model of Chinese painting can achieve high accuracy and obvious acceleration effect. More importantly, the emotion recognition and analysis effect of traditional Chinese painting is the best, which can provide an experimental basis for the digital understanding and management of emotion of quintessence.

Neural Network Model for Assessing the Physical and Mechanical Properties of a Metal Material Based on Deep Learning

2020 ◽  
pp. 18-28
Author(s):  
Andrei Kliuev ◽  
Roman Klestov ◽  
Valerii Stolbov
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Deep Neural Network ◽  
Physical And Mechanical Properties ◽  
Training Set ◽  
Test Set ◽  
Algorithmic Stability ◽  
Test Sets ◽  
Trained Network ◽  
Basic Test

The paper investigates the algorithmic stability of learning a deep neural network in problems of recognition of the materials microstructure. It is shown that at 8% of quantitative deviation in the basic test set the algorithm trained network loses stability. This means that with such a quantitative or qualitative deviation in the training or test sets, the results obtained with such trained network can hardly be trusted. Although the results of this study are applicable to the particular case, i.e. problems of recognition of the microstructure using ResNet-152, the authors propose a cheaper method for studying stability based on the analysis of the test, rather than the training set.

scholarly journals Identification Method for Series Arc Faults Based on Wavelet Transform and Deep Neural Network

Energies ◽  
2019 ◽  
Vol 13 (1) ◽  
pp. 142 ◽  
Author(s):  
Qiongfang Yu ◽  
Yaqian Hu ◽  
Yi Yang
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Power Supply ◽  
Distribution Systems ◽  
Deep Neural Network ◽  
Experimental Result ◽  
Discrete Wavelet ◽  
Training Set ◽  
Test Set ◽  
Power Distribution System

The power supply quality and power supply safety of a low-voltage residential power distribution system is seriously affected by the occurrence of series arc faults. It is difficult to detect and extinguish them due to the characteristics of small current, high stochasticity, and strong concealment. In order to improve the overall safety of residential distribution systems, a novel method based on discrete wavelet transform (DWT) and deep neural network (DNN) is proposed to detect series arc faults in this paper. An experimental bed is built to obtain current signals under two states, normal and arcing. The collected signals are discomposed in different scales applying the DWT. The wavelet coefficient sequences are used for forming training set and test set. The deep neural network trained by training set under 4 different loads adaptively learn the feature of arc faults. The accuracy of arc faults recognition is sent through feeding test set into the model, about 97.75%. The experimental result shows that this method has good accuracy and generality under different types of loading.

Sign in / Sign up

Export Citation Format

Share Document