scholarly journals Deep-insight visible neural network (DI-VNN) for improving interpretability of a non-image deep learning model by data-driven ontology

2021 ◽  
Author(s):  
Herdiantri Sufriyana ◽  
Yu Wei Wu ◽  
Emily Chia-Yu Su
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Predictive Ability ◽  
Image Data ◽  
Data Driven ◽  
Differential Analysis ◽  
Model Training ◽  
Internal Properties ◽  
Using Data ◽  
Construction Model

Abstract We aimed to provide a framework that organizes internal properties of a convolutional neural network (CNN) model using non-image data to be interpretable by human. The interface was represented as ontology map and network respectively by dimensional reduction and hierarchical clustering techniques. The applicability is to implement a prediction model either to classify categorical or to estimate numerical outcome, including but not limited to that using data from electronic health records. This pipeline harnesses invention of CNN algorithms for non-image data while improving the depth of interpretability by data-driven ontology. However, the DI-VNN is only for exploration beyond its predictive ability, which requires further explanatory studies, and needs a human user with specific competences in medicine, statistics, and machine learning to explore the DI-VNN with high confidence. The key stages consisted of data preprocessing, differential analysis, feature mapping, network architecture construction, model training and validation, and exploratory analysis.

scholarly journals Data-Driven Stability Assessment of Multilayer Long Short-Term Memory Networks

2021 ◽  
Vol 11 (4) ◽  
pp. 1829
Author(s):  
Davide Grande ◽  
Catherine A. Harris ◽  
Giles Thomas ◽  
Enrico Anderlini
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Short Term Memory ◽  
Moving Average ◽  
Machine Learning Algorithms ◽  
Physical Models ◽  
Data Driven ◽  
The Stability ◽  
And Control ◽  
Nonlinear Autoregressive

Recurrent Neural Networks (RNNs) are increasingly being used for model identification, forecasting and control. When identifying physical models with unknown mathematical knowledge of the system, Nonlinear AutoRegressive models with eXogenous inputs (NARX) or Nonlinear AutoRegressive Moving-Average models with eXogenous inputs (NARMAX) methods are typically used. In the context of data-driven control, machine learning algorithms are proven to have comparable performances to advanced control techniques, but lack the properties of the traditional stability theory. This paper illustrates a method to prove a posteriori the stability of a generic neural network, showing its application to the state-of-the-art RNN architecture. The presented method relies on identifying the poles associated with the network designed starting from the input/output data. Providing a framework to guarantee the stability of any neural network architecture combined with the generalisability properties and applicability to different fields can significantly broaden their use in dynamic systems modelling and control.

scholarly journals Multiattentive Recurrent Neural Network Architecture for Multilingual Readability Assessment

2019 ◽  
Vol 7 ◽  
pp. 421-436 ◽  
Author(s):  
Ion Madrazo Azpiazu ◽  
Maria Soledad Pera
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Network Architecture ◽  
Text Structure ◽  
Reading Level ◽  
Data Sets ◽  
Neural Network Architecture ◽  
Using Data ◽  
Word Attention ◽  
Readability Assessment

We present a multiattentive recurrent neural network architecture for automatic multilingual readability assessment. This architecture considers raw words as its main input, but internally captures text structure and informs its word attention process using other syntax- and morphology-related datapoints, known to be of great importance to readability. This is achieved by a multiattentive strategy that allows the neural network to focus on specific parts of a text for predicting its reading level. We conducted an exhaustive evaluation using data sets targeting multiple languages and prediction task types, to compare the proposed model with traditional, state-of-the-art, and other neural network strategies.

scholarly journals Application of Genetic Algorithms for the Selection of Neural Network Architecture in the Monitoring System for Patients with Parkinson’s Disease

2021 ◽  
Vol 11 (12) ◽  
pp. 5470
Author(s):  
Yulia Shichkina ◽  
Yulia Irishina ◽  
Elizaveta Stanevich ◽  
Armando de Jesus Plasencia Salgueiro
Keyword(s):  
Neural Network ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Genetic Algorithms ◽  
Monitoring System ◽  
Network Architecture ◽  
Hybrid Approach ◽  
Neural Network Architecture ◽  
The Neural Network ◽  
Using Data

This article describes an approach for collecting and pre-processing phone owner data, including their voice, in order to classify their condition using data mining methods. The most important research results presented in this article are the developed approaches for the processing of patient voices and the use of genetic algorithms to select the architecture of the neural network in the monitoring system for patients with Parkinson’s disease. The process used to pre-process a person’s voice is described in order to determine the main parameters that can be used in assessing a person’s condition. It is shown that the efficiency of using genetic algorithms for constructing neural networks depends on the composition of the data. As a result, the best result in the accuracy of assessing the patient’s condition can be obtained by a hybrid approach, where a part of the neural network architecture is selected analytically manually, while the other part is built automatically.

scholarly journals Bankruptcy Prediction for Innovative Companies

2021 ◽  
Vol 15 (4) ◽  
pp. 36-55
Author(s):  
Ivan Lobeev
Keyword(s):  
Neural Network ◽  
Financial Distress ◽  
Network Architecture ◽  
Relevant Literature ◽  
Predictive Ability ◽  
Bankruptcy Prediction ◽  
Financial Data ◽  
The Novel ◽  
Novel Approach ◽  
Bankruptcy Probability

The main purpose of this article is to identify the best neural network model algorithm and relevant set of variables for predicting financial distress/bankruptcy in innovative companies. While previous articles in this area considered neural network analysis for large companies from primary sectors of the economy, we take the novel approach of examining theless-explored area of innovative companies. First, we complete a comprehensive review of the relevant literature in order to define the best configuration of factors which can influence bankruptcy, network architecture and learning methodology. We apply our chosen method to a sample of companies from around the world, from industries which are considered innovative, and identify the dependence of bankruptcy probability on a set of factors which are reflected in the financial data of a company. Our evaluation is based on the financial data of 300 companies – 50 of them are bankrupts, and 250 are ‘healthy’. Our results represent the set of relevant factors for bankruptcy prediction and the appropriate neural network. We have applied a total of 19 factors characterising efficiency, liquidity, profitability, sustainability, and level of innovation. Our proposed analysis is appropriate for all sizes of companies. We provided two models in order to cater for the most confidence in terms of obtained results. The total predictive ability of the model developed in our research is almost 98%, which is extremely efficient, and corresponds to the results of the most modern methods. Both approaches demonstrated almost the same level of influence of factor groups on final bankruptcy probability.

scholarly journals Self-consistent electron–THF cross sections derived using data-driven swarm analysis with a neural network model

2020 ◽  
Vol 29 (10) ◽  
pp. 105008
Author(s):  
P W Stokes ◽  
M J E Casey ◽  
D G Cocks ◽  
J de Urquijo ◽  
G García ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Cross Sections ◽  
Neural Network Model ◽  
Data Driven ◽  
Self Consistent ◽  
Using Data

scholarly journals Deep-Data-Driven Neural Networks for COVID-19 Vaccine Efficacy

Epidemiologia ◽  
2021 ◽  
Vol 2 (4) ◽  
pp. 564-586
Author(s):  
Thomas K. Torku ◽  
Abdul Q. M. Khaliq ◽  
Khaled M. Furati
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Hybrid Approach ◽  
Vaccination Rate ◽  
Data Driven ◽  
Efficacy Rate ◽  
Feed Forward Neural Network ◽  
Health Authorities ◽  
Public Health Authorities ◽  
The Impact

Vaccination strategies to lessen the impact of the spread of a disease are fundamental to public health authorities and policy makers. The socio-economic benefit of full return to normalcy is the core of such strategies. In this paper, a COVID-19 vaccination model with efficacy rate is developed and analyzed. The epidemiological parameters of the model are learned via a feed-forward neural network. A hybrid approach that combines residual neural network with variants of recurrent neural network is implemented and analyzed for reliable and accurate prediction of daily cases. The error metrics and a k-fold cross validation with random splitting reveal that a particular type of hybrid approach called residual neural network with gated recurrent unit is the best hybrid neural network architecture. The data-driven simulations confirm the fact that the vaccination rate with higher efficacy lowers the infectiousness and basic reproduction number. As a study case, COVID-19 data for the state of Tennessee in USA is used.

scholarly journals A physics-informed neural network for sound propagation in the atmospheric boundary layer

2021 ◽  
Author(s):  
Chris Pettit ◽  
D. Wilson
Keyword(s):  
Neural Network ◽  
Boundary Layer ◽  
Atmospheric Boundary Layer ◽  
Loss Function ◽  
Sound Speed ◽  
Network Architecture ◽  
Sound Propagation ◽  
Transmission Loss ◽  
Training Data ◽  
Data Driven

We describe what we believe is the first effort to develop a physics-informed neural network (PINN) to predict sound propagation through the atmospheric boundary layer. PINN is a recent innovation in the application of deep learning to simulate physics. The motivation is to combine the strengths of data-driven models and physics models, thereby producing a regularized surrogate model using less data than a purely data-driven model. In a PINN, the data-driven loss function is augmented with penalty terms for deviations from the underlying physics, e.g., a governing equation or a boundary condition. Training data are obtained from Crank-Nicholson solutions of the parabolic equation with homogeneous ground impedance and Monin-Obukhov similarity theory for the effective sound speed in the moving atmosphere. Training data are random samples from an ensemble of solutions for combinations of parameters governing the impedance and the effective sound speed. PINN output is processed to produce realizations of transmission loss that look much like the Crank-Nicholson solutions. We describe the framework for implementing PINN for outdoor sound, and we outline practical matters related to network architecture, the size of the training set, the physics-informed loss function, and challenge of managing the spatial complexity of the complex pressure.

Sign in / Sign up

Export Citation Format

Share Document