A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Representation Learning with Statistical Independence to Mitigate Bias
[article]
2020
arXiv
pre-print
Controlling for all types of biases in the dataset curation stage is cumbersome and sometimes impossible. ...
We apply our method to synthetic data, medical images (containing task bias), and a dataset for gender classification (containing dataset bias). ...
We evaluated our bias-resilient neural network (BR-Net) on synthetic, medical diagnosis, and gender classification datasets. ...
arXiv:1910.03676v4
fatcat:yf6amgpfivgarmfunohtx3l2ry
Accuracy and Resiliency of Analog Compute-in-Memory Inference Engines
[article]
2020
arXiv
pre-print
Recently, analog compute-in-memory (CIM) architectures based on emerging analog non-volatile memory (NVM) technologies have been explored for deep neural networks (DNN) to improve energy efficiency. ...
Simulation results show that DNNs trained for high-precision digital computing engines are not resilient against the uncertainty of the analog NVM devices. ...
Fig. 4 shows the performance of the neural networks with and without matching the range of weights and biases. ...
arXiv:2008.02400v1
fatcat:xil2eskt45d67du4hms7n4tgke
On the Comparison of Deep Learning Neural Network and Binary Logistic Regression for Classifying the Acceptance Status of Bidikmisi Scholarship Applicants in East Java
2018
MATEMATIKA
One form of Neural Network model available for various applications is the Resilient Backpropagation Neural Network (Resilient BPNN). ...
This study aims to compare the performance of the Resilient BPNN method as a Deep Learning Neural Network and Binary Logistic Regression method in determining the classification of Bidikmisi scholarship ...
Backpropagation Neural Network (Resilient BPNN) Artificial neural network learning algorithm Backpropagation was first formulated by Werbos [9] and popularized by Rummelhart and Mc. ...
doi:10.11113/matematika.v34.n3.1141
fatcat:o2u6ao62uba2hnmghfj4xv7lqy
Evaluating the components of social and economic resilience: After two large earthquake disasters Rudbar 1990 and Bam 2003
2017
Jàmbá : Journal of Disaster Risk Studies
Data were analysed using multiple linear regression and feedforward multilayer perceptron artificial neural network. ...
Neural network analysis revealed that social capital and employment recovery are the most and least effective factors, respectively, in both cities. ...
The major difference between an artificial network and other neural network models is the ability to learn. ...
doi:10.4102/jamba.v9i1.368
pmid:29955334
pmcid:PMC6014119
fatcat:oivupdbanfcllaapcvz33dq3hm
Neural Network Approach for Software Defect Prediction Based on Quantitative and Qualitative Factors
2012
Journal of clean energy technologies
Index Terms-Neural network, quantitive, qualittative, software fault, defect data, and software quality ...
Backpropagation (RB) based neural network approach to identify the relation between the various qualitative as well as quantitative factor of the modules with the number of faults present in the module ...
are experimented for training a neural network separately. ...
doi:10.7763/ijcte.2012.v4.470
fatcat:hhqzttqb35eenjjhczpnvvqqam
Editorial: Positive Neuroscience: the Neuroscience of Human Flourishing
2020
Frontiers in Human Neuroscience
Instead of focusing on pathology, research on positive neuroscience directs its attention on the neural mechanisms supporting flourishing, psychological well-being, resilience, and promotion of health. ...
Kress and Aue begin this topic with a behavioral study on the effect of attention bias modification on optimism bias-that is, being overly optimistic-for future positive events. ...
Second, Kwak et al. explored the neural mechanisms underlying the effect of a 4-days meditation intervention on stress resilience using resting state fMRI FC. ...
doi:10.3389/fnhum.2020.00047
pmid:32184713
pmcid:PMC7058787
fatcat:ozftarkyvfah3pxgwnapfw4rn4
Effect of Training Algorithms on the Performance of ANN for Pattern Recognition of Bivariate Process
2013
International Journal of Computer Applications
Artificial Neural Network (ANN) which is designed to mimic the human brain have been used in the literature for identifying variable(s) that is(are) responsible for out-ofcontrol signal and the training ...
The result of study shows that the Levenberg-Marquardt (trainlm) is the best algorithm for pattern recognition of bivariate manufacturing process in terms of recognition accuracy and the resilient backpropagation ...
errors with respect to the weights and biases and e is a vector of network errors. ...
doi:10.5120/12085-8031
fatcat:cseeoish7bggvnhcfnijpotxde
Does Pygmalion effect and Psycap Impact Academic Performance?
2020
International journal of modern trends in science and technology
This study aims to identify how educationists can use Neural Networking to understand the impact of the predictors' namely internal factor (Psychological capital) and external factor (Self Fulfilling Prophecy ...
The statistical tools used were weighted mean and neural networking. ...
FINDINGS AND DISCUSSIONS
NEURAL NETWORKING Multilayer Perceptron type neural networks consist of neurons or nodes which are information processing units arranged in three layers and interconnected by ...
doi:10.46501/ijmtst061017
fatcat:2xk3i5zjeffzdpo4xarfo7hxfa
Artificial Neural Network based Defect Detection of Welds in TOFD Technique
2012
International Journal of Computer Applications
The classification reliability of defects detected by this technique can be improved by applying the Artificial Neural Network. ...
A multi layer feed forward network with Resilient Back Propagation algorithm has been applied for classification of the signals. The number of hidden layers in the network are increased from 0 to 6. ...
of weights of the layers' connections according to the back propagation learning algorithm. trainrp is a network training function that updates weight and bias values according to the resilient backpropagation ...
doi:10.5120/5808-8069
fatcat:w44qgwasljdavgrc6iorwwxppy
With Greater Distance Comes Worse Performance: On the Perspective of Layer Utilization and Model Generalization
[article]
2022
arXiv
pre-print
the neural network size. ...
that take the internal structure of neural networks into consideration. ...
Under the traditional bias-variance trade-off theory, complex networks should easily overfit training data. ...
arXiv:2201.11939v1
fatcat:pwmlbhb2ubaihelkdzwlnmzsj4
Deep Neural Network-Based Storey Drift Modelling of Precast Concrete Structures Using RStudio
2021
Journal of Soft Computing in Civil Engineering
In this research, storey drift has been determined using Deep neural networks (DNN Keras). ...
back-propagation neural networks (BPNN), indicating that DNN Keras has about 8 per cent improved efficiency in predicting storey drift. ...
Each node has its associated weight and bias, weight is a factor inside a neural network that converts input data into hidden layers of the network. ...
doi:10.22115/scce.2021.289034.1329
doaj:094e422d64534310bdb359e84b8e86c6
fatcat:mx65tgaudfcg3ba6dbukhf6rea
Artificial Neural Network Parameter Tuning Framework For Heart Disease Classification
2018
Proceeding of the Electrical Engineering Computer Science and Informatics
Keywords-artificial neural network, heart disease classification, artificial neural network parameter tuning, statlog heart dataset, cleveland heart dataset. I. ...
This paper proposed the parameter tuning framework for artificial neural network. ...
The neural network model with optimize parameters and the best weight and bias is simulated using test dataset for evaluation. ...
doi:10.11591/eecsi.v5.1695
fatcat:3yq7xxsi6jgonc35op4mz4vfzq
The most accurate ANN learning algorithm for FEM prediction of mechanical performance of alloy A356
2012
Kovové materiály
After the preparation of the training set, the neural network was trained using different training algorithms, hidden layers and neuron numbers in hidden layers. ...
In order to discover the most accurate prediction of yield stress, UTS and elongation percentage, the effects of various training algorithms on learning performance of the neural networks were investigated ...
-Resilient back propagation (Rprop): is a network training function that updates weight and bias values according to the resilient back propagation algorithm. ...
doi:10.4149/km_2012_1_25
fatcat:oqtpyg54jvcyjccyocl7tp3t4m
Peramalan Jumlah Penumpang Kereta Api di Indonesia dengan Resilient Back-Propagation (Rprop) Neural Network
2018
Mantik: Jurnal Matematika
From the results of data analysis conducted, it can be concluded that the performance of neural network model with Resilient Back-propagation (Rprop) formed from training data gives very accurate prediction ...
The prediction method of Back-propagation Neural Network (BPNN) has relatively slow convergence. ...
Gradien adalah kumpulan semua turunan parsial untuk semua bobot dan bias dari neural network. ...
doi:10.15642/mantik.2018.4.2.90-99
fatcat:lcrpchxjdzduhl34b63cok7lba
FTT-NAS: Discovering Fault-Tolerant Convolutional Neural Architecture
[article]
2021
arXiv
pre-print
We propose Fault-Tolerant Neural Architecture Search (FT-NAS) to automatically discover convolutional neural network (CNN) architectures that are reliable to various faults in nowadays devices. ...
When deploying neural networks (NNs) onto the devices under complex environments, there are various types of possible faults: soft errors caused by cosmic radiation and radioactive impurities, voltage ...
neural networks [12] . ...
arXiv:2003.10375v2
fatcat:2fmahmgy7rckvlqaobtd6jco2i
« Previous
Showing results 1 — 15 out of 12,811 results