scholarly journals Transfer Learning for Multi-Premise Entailment with Relationship Processing Module

2021 ◽  
Vol 13 (3) ◽  
pp. 71
Author(s):  
Pin Wu ◽  
Rukang Zhu ◽  
Zhidan Lei
Keyword(s):  
Neural Network ◽  
Transfer Learning ◽  
Training Data ◽  
Specific Structure ◽  
Training Method ◽  
Test Set ◽  
The Neural Network ◽  
Processing Module ◽  
The Relationship

Using the single premise entailment (SPE) model to accomplish the multi-premise entailment (MPE) task can alleviate the problem that the neural network cannot be effectively trained due to the lack of labeled multi-premise training data. Moreover, the abundant judgment methods for the relationship between sentence pairs can also be applied in this task. However, the single-premise pre-trained model does not have a structure for processing multi-premise relationships, and this structure is a crucial technique for solving MPE problems. This paper proposes adding a multi-premise relationship processing module based on not changing the structure of the pre-trained model to compensate for this deficiency. Moreover, we proposed a three-step training method combining this module, which ensures that the module focuses on dealing with the multi-premise relationship during matching, thus applying the single-premise model to multi-premise tasks. Besides, this paper also proposes a specific structure of the relationship processing module, i.e., we call it the attention-backtracking mechanism. Experiments show that this structure can fully consider the context of multi-premise, and the structure combined with the three-step training can achieve better accuracy on the MPE test set than other transfer methods.

Prediction and analysis of thermal aging behavior of magnetorheological grease

2021 ◽  
Author(s):  
Guangxin Yang ◽  
Jiabao Pan ◽  
Dongdong Ye ◽  
Kaiqiang Ye ◽  
Hong Gao
Keyword(s):  
Neural Network ◽  
Thermal Aging ◽  
Magnetic Coupling ◽  
Training Data ◽  
Heating Process ◽  
Aging Behavior ◽  
The Neural Network ◽  
New Type ◽  
Artificial Neural Network Ann ◽  
The Relationship

Abstract Magnetorheological grease (MRG) is a new type of field-response intelligent material with controllable performance and excellent settlement stability, which is feasible to replace traditional materials. The heating phenomenon of magnetorheological (MR) devices is more common during operation, while the MRG as a medium has more significant thermal rheological characteristics in the heating process. In the process of MRG modeling, a model is established to study the effect of thermal-magnetic coupling on its performance and to save experimental time and reduce costs. Hence, an improved and reliable artificial neural network (ANN) prediction model is established to characterize and predict the relationship among temperature, aging time, magnetic field strength and thermal-rheological properties of MRG. The training data of neural network were obtained from the experiments under the condition of thermomagnetic coupling with rotational rheometer. After the neural network was trained and substituted into the test set data, the predicted results were compared with the experimental results, the correlation coefficient R reached and exceeded 0.95. The results show that the model has excellent prediction accuracy and can provide theoretical reference for the thermal aging behavior of MRG.

scholarly journals Rethinking the Random Cropping Data Augmentation Method Used in the Training of CNN-Based SAR Image Ship Detector

2020 ◽  
Vol 13 (1) ◽  
pp. 34
Author(s):  
Rong Yang ◽  
Robert Wang ◽  
Yunkai Deng ◽  
Xiaoxue Jia ◽  
Heng Zhang
Keyword(s):  
Neural Network ◽  
Data Augmentation ◽  
Back Propagation ◽  
Detection Performance ◽  
Training Data ◽  
Sar Image ◽  
Optical Images ◽  
The Neural Network ◽  
Effective Training ◽  
Standard Configuration

The random cropping data augmentation method is widely used to train convolutional neural network (CNN)-based target detectors to detect targets in optical images (e.g., COCO datasets). It can expand the scale of the dataset dozens of times while consuming only a small amount of calculations when training the neural network detector. In addition, random cropping can also greatly enhance the spatial robustness of the model, because it can make the same target appear in different positions of the sample image. Nowadays, random cropping and random flipping have become the standard configuration for those tasks with limited training data, which makes it natural to introduce them into the training of CNN-based synthetic aperture radar (SAR) image ship detectors. However, in this paper, we show that the introduction of traditional random cropping methods directly in the training of the CNN-based SAR image ship detector may generate a lot of noise in the gradient during back propagation, which hurts the detection performance. In order to eliminate the noise in the training gradient, a simple and effective training method based on feature map mask is proposed. Experiments prove that the proposed method can effectively eliminate the gradient noise introduced by random cropping and significantly improve the detection performance under a variety of evaluation indicators without increasing inference cost.

Application of ANN Back-Propagation for Fracture Design Parameters in Extra-Low Cycle Rotating Bending Fatigue

2009 ◽  
Vol 610-613 ◽  
pp. 450-453
Author(s):  
Hong Yan Duan ◽  
You Tang Li ◽  
Jin Zhang ◽  
Gui Ping He
Keyword(s):  
Neural Network ◽  
Neural Network Model ◽  
Back Propagation ◽  
Training Data ◽  
Design Parameters ◽  
Ann Model ◽  
Bending Fatigue ◽  
The Neural Network ◽  
Rotating Bending Fatigue ◽  
Rotating Bending

The fracture problems of ecomaterial (aluminum alloyed cast iron) under extra-low cycle rotating bending fatigue loading were studied using artificial neural networks (ANN) in this paper. The training data were used in the formation of training set of ANN. The ANN model exhibited excellent in results comparison with the experimental results. It was concluded that predicted fracture design parameters by the trained neural network model seem more reasonable compared to approximate methods. It is possible to claim that, ANN is fairly promising prediction technique if properly used. Training ANN model was introduced at first. And then the Training data for the development of the neural network model was obtained from the experiments. The input parameters, notch depth, the presetting deflection and tip radius of the notch, and the output parameters, the cycle times of fracture were used during the network training. The neural network architecture is designed. The ANN model was developed using back propagation architecture with three layers jump connections, where every layer was connected or linked to every previous layer. The number of hidden neurons was determined according to special formula. The performance of system is summarized at last. In order to facilitate the comparisons of predicted values, the error evaluation and mean relative error are obtained. The result show that the training model has good performance, and the experimental data and predicted data from ANN are in good coherence.

scholarly journals Study on process of chemical fiber filament automatic doffing system based on simulation platform and machine learning

2021 ◽  
Vol 16 ◽  
pp. 155892502110548
Author(s):  
Hongxin Zhu ◽  
Kun Zou ◽  
Wenlan Bao
Keyword(s):  
Neural Network ◽  
Linear Regression ◽  
Multiple Linear Regression ◽  
Production Line ◽  
Simulation Platform ◽  
Chemical Fiber ◽  
Production Lines ◽  
The Neural Network ◽  
Spss Software ◽  
The Relationship

In recent years, a large number of automatic equipment has been introduced into the chemical fiber filament doffing production line, but the related research on the fully automatic production line technology is not yet mature. At present, it is difficult to collect data due to test costs and confidentiality. This paper proposes to develop a simulation platform for a chemical fiber filament doffing production line, which enables us to effectively obtain data and quantitatively study the relationship between the number of manual interventions and other process parameters of the production line. Considering that the parameter research is a multi-factor problem, an orthogonal test was designed by using SPSS software and was carried out by using a simulation platform. The multiple linear regression (MLR) and the neural network optimized by genetic algorithm were adopted to fit the relationship between the number of manual interventions and other parameters of the production line. The SPSS software was applied to obtain the standardized coefficients of the multiple linear regression fitting and the neural network mean impact value (MIV) algorithm was applied to obtain the magnitude and direction of the impact of different parameters on the number of manual interventions. The above results provide important reference for the design of similar new production lines and for the improvement of old production lines.

scholarly journals Bootstrapping a Neural Morphological Generator from Morphological Analyzer Output for Inuktitut

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Jeffrey Micher
Keyword(s):  
Neural Network ◽  
Training Data ◽  
Data Set ◽  
Set Size ◽  
The Neural Network ◽  
Surface Character ◽  
Finite State ◽  
Character Sequences ◽  
Finite State Transducer

We present a method for building a morphological generator from the output of an existing analyzer for Inuktitut, in the absence of a two-way finite state transducer which would normally provide this functionality. We make use of a sequence to sequence neural network which “translates” underlying Inuktitut morpheme sequences into surface character sequences. The neural network uses only the previous and the following morphemes as context. We report a morpheme accuracy of approximately 86%. We are able to increase this accuracy slightly by passing deep morphemes directly to output for unknown morphemes. We do not see significant improvement when increasing training data set size, and postulate possible causes for this.

Analysis of Fin-Tube Evaporator Performance With Limited Experimental Data Using Artificial Neural Networks

2000 ◽  
Author(s):  
Arturo Pacheco-Vega ◽  
Mihir Sen ◽  
Rodney L. McClain
Keyword(s):  
Neural Network ◽  
Heat Rate ◽  
Network Models ◽  
Activation Function ◽  
Operating Conditions ◽  
Training Data ◽  
Neural Network Models ◽  
The Neural Network ◽  
Artificial Neural ◽  
Fin Tube

Abstract In the current study we consider the problem of accuracy in heat rate estimations from artificial neural network models of heat exchangers used for refrigeration applications. The network configuration is of the feedforward type with a sigmoid activation function and a backpropagation algorithm. Limited experimental measurements from a manufacturer are used to show the capability of the neural network technique in modeling the heat transfer in these systems. Results from this exercise show that a well-trained network correlates the data with errors of the same order as the uncertainty of the measurements. It is also shown that the number and distribution of the training data are linked to the performance of the network when estimating the heat rates under different operating conditions, and that networks trained from few tests may give large errors. A methodology based on the cross-validation technique is presented to find regions where not enough data are available to construct a reliable neural network. The results from three tests show that the proposed methodology gives an upper bound of the estimated error in the heat rates.

Oversampling Based on Data Augmentation in Convolutional Neural Network for Silicon Wafer Defect Classification

2020 ◽  
Author(s):  
Uzma Batool ◽  
Mohd Ibrahim Shapiai ◽  
Nordinah Ismail ◽  
Hilman Fauzi ◽  
Syahrizal Salleh
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Silicon Wafer ◽  
Data Augmentation ◽  
Imbalanced Data ◽  
Training Data ◽  
Defect Classification ◽  
Learning Method ◽  
Test Set

Silicon wafer defect data collected from fabrication facilities is intrinsically imbalanced because of the variable frequencies of defect types. Frequently occurring types will have more influence on the classification predictions if a model gets trained on such skewed data. A fair classifier for such imbalanced data requires a mechanism to deal with type imbalance in order to avoid biased results. This study has proposed a convolutional neural network for wafer map defect classification, employing oversampling as an imbalance addressing technique. To have an equal participation of all classes in the classifier’s training, data augmentation has been employed, generating more samples in minor classes. The proposed deep learning method has been evaluated on a real wafer map defect dataset and its classification results on the test set returned a 97.91% accuracy. The results were compared with another deep learning based auto-encoder model demonstrating the proposed method, a potential approach for silicon wafer defect classification that needs to be investigated further for its robustness.

scholarly journals Improving Regional and Teleseismic Detection for Single-Trace Waveforms Using a Deep Temporal Convolutional Neural Network Trained with an Array-Beam Catalog

Sensors ◽  
2019 ◽  
Vol 19 (3) ◽  
pp. 597 ◽  
Author(s):  
Joshua Dickey ◽  
Brett Borghetti ◽  
William Junek
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Detection Performance ◽  
Training Data ◽  
Characteristic Functions ◽  
Type I ◽  
Test Set ◽  
Arrival Times ◽  
Treaty Monitoring ◽  
Single Trace

The detection of seismic events at regional and teleseismic distances is critical to Nuclear Treaty Monitoring. Traditionally, detecting regional and teleseismic events has required the use of an expensive multi-instrument seismic array; however in this work, we present DeepPick, a novel seismic detection algorithm capable of array-like detection performance from a single-trace. We achieve this performance through three novel steps: First, a high-fidelity dataset is constructed by pairing array-beam catalog arrival-times with single-trace waveforms from the reference instrument of the array. Second, an idealized characteristic function is created, with exponential peaks aligned to the cataloged arrival times. Third, a deep temporal convolutional neural network is employed to learn the complex non-linear filters required to transform the single-trace waveforms into corresponding idealized characteristic functions. The training data consists of all arrivals in the International Seismological Centre Database for seven seismic arrays over a five year window from 1 January 2010 to 1 January 2015, yielding a total training set of 608,362 detections. The test set consists of the same seven arrays over a one year window from 1 January 2015 to 1 January 2016. We report our results by training the algorithm on six of the arrays and testing it on the seventh, so as to demonstrate the generalization and transportability of the technique to new stations. Detection performance against this test set is outstanding, yielding significant improvements in recall over existing techniques. Fixing a type-I error rate of 0.001, the algorithm achieves an overall recall (true positive rate) of 56% against the 141,095 array-beam arrivals in the test set, yielding 78,802 correct detections. This is more than twice the 37,572 detections made by an STA/LTA detector over the same period, and represents a 35% improvement over the 58,515 detections made by a state-of-the-art kurtosis-based detector. Furthermore, DeepPick provides at least a 4 dB improvement in detector sensitivity across the board, and is more computationally efficient, with run-times an order of magnitude faster than either of the other techniques tested. These results demonstrate the potential of our algorithm to significantly enhance the effectiveness of the global treaty monitoring network.

scholarly journals Predicting Wins, Losses and Attributes’ Sensitivities in the Soccer World Cup 2018 Using Neural Network Analysis

Sensors ◽  
2020 ◽  
Vol 20 (11) ◽  
pp. 3213 ◽  
Author(s):  
Amr Hassan ◽  
Abdel-Rahman Akl ◽  
Ibrahim Hassan ◽  
Caroline Sunderland
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Average Distance ◽  
Deep Understanding ◽  
The Neural Network ◽  
Testing Error ◽  
Training Error ◽  
Using Data ◽  
The Relationship

Predicting the results of soccer competitions and the contributions of match attributes, in particular, has gained popularity in recent years. Big data processing obtained from different sensors, cameras and analysis systems needs modern tools that can provide a deep understanding of the relationship between this huge amount of data produced by sensors and cameras, both linear and non-linear data. Using data mining tools does not appear sufficient to provide a deep understanding of the relationship between the match attributes and results and how to predict or optimize the results based upon performance variables. This study aimed to suggest a different approach to predict wins, losses and attributes’ sensitivities which enables the prediction of match results based on the most sensitive attributes that affect it as a second step. A radial basis function neural network model has successfully weighted the effectiveness of all match attributes and classified the team results into the target groups as a win or loss. The neural network model’s output demonstrated a correct percentage of win and loss of 83.3% and 72.7% respectively, with a low Root Mean Square training error of 2.9% and testing error of 0.37%. Out of 75 match attributes, 19 were identified as powerful predictors of success. The most powerful respectively were: the Total Team Medium Pass Attempted (MBA) 100%; the Distance Covered Team Average in zone 3 (15–20 km/h; Zone3_TA) 99%; the Team Average ball delivery into the attacking third of the field (TA_DAT) 80.9%; the Total Team Covered Distance without Ball Possession (Not in_Poss_TT) 76.8%; and the Average Distance Covered by Team (Game TA) 75.1%. Therefore, the novel radial based function neural network model can be employed by sports scientists to adapt training, tactics and opposition analysis to improve performance.

Sign in / Sign up

Export Citation Format

Share Document