A neural network assisted Metropolis adjusted Langevin algorithm

2020 ◽  
Vol 26 (2) ◽  
pp. 93-111
Author(s):  
Christian Müller ◽  
Holger Diedam ◽  
Thomas Mrziglod ◽  
Andreas Schuppert
Keyword(s):  
Neural Network ◽  
Blood Coagulation ◽  
Likelihood Function ◽  
State Of The Art ◽  
Mcmc Algorithm ◽  
Convex Shape ◽  
Mcmc Algorithms ◽  
The Neural Network ◽  
Random Walk Metropolis ◽  
The Impact

AbstractIn this paper, we derive a Markov chain Monte Carlo (MCMC) algorithm supported by a neural network. In particular, we use the neural network to substitute derivative calculations made during a Metropolis adjusted Langevin algorithm (MALA) step with inexpensive neural network evaluations. Using a complex, high-dimensional blood coagulation model and a set of measurements, we define a likelihood function on which we evaluate the new MCMC algorithm. The blood coagulation model is a dynamic model, where derivative calculations are expensive and hence limit the efficiency of derivative-based MCMC algorithms. The MALA adaptation greatly reduces the time per iteration, while only slightly affecting the sample quality. We also test the new algorithm on a 2-dimensional example with a non-convex shape, a case where the MALA algorithm has a clear advantage over other state of the art MCMC algorithms. To assess the impact of the new algorithm, we compare the results to previously generated results of the MALA and the random walk Metropolis Hastings (RWMH).

scholarly journals DANNP: an efficient artificial neural network pruning tool

2017 ◽  
Vol 3 ◽  
pp. e137 ◽  
Author(s):  
Mona Alshahrani ◽  
Othman Soufan ◽  
Arturo Magana-Mora ◽  
Vladimir B. Bajic
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Model Performance ◽  
Training Data ◽  
Classification Problems ◽  
Link Type ◽  
On Line ◽  
Pruning Algorithms ◽  
Artificial Neural ◽  
The Impact

Background Artificial neural networks (ANNs) are a robust class of machine learning models and are a frequent choice for solving classification problems. However, determining the structure of the ANNs is not trivial as a large number of weights (connection links) may lead to overfitting the training data. Although several ANN pruning algorithms have been proposed for the simplification of ANNs, these algorithms are not able to efficiently cope with intricate ANN structures required for complex classification problems. Methods We developed DANNP, a web-based tool, that implements parallelized versions of several ANN pruning algorithms. The DANNP tool uses a modified version of the Fast Compressed Neural Network software implemented in C++ to considerably enhance the running time of the ANN pruning algorithms we implemented. In addition to the performance evaluation of the pruned ANNs, we systematically compared the set of features that remained in the pruned ANN with those obtained by different state-of-the-art feature selection (FS) methods. Results Although the ANN pruning algorithms are not entirely parallelizable, DANNP was able to speed up the ANN pruning up to eight times on a 32-core machine, compared to the serial implementations. To assess the impact of the ANN pruning by DANNP tool, we used 16 datasets from different domains. In eight out of the 16 datasets, DANNP significantly reduced the number of weights by 70%–99%, while maintaining a competitive or better model performance compared to the unpruned ANN. Finally, we used a naïve Bayes classifier derived with the features selected as a byproduct of the ANN pruning and demonstrated that its accuracy is comparable to those obtained by the classifiers trained with the features selected by several state-of-the-art FS methods. The FS ranking methodology proposed in this study allows the users to identify the most discriminant features of the problem at hand. To the best of our knowledge, DANNP (publicly available at www.cbrc.kaust.edu.sa/dannp) is the only available and on-line accessible tool that provides multiple parallelized ANN pruning options. Datasets and DANNP code can be obtained at www.cbrc.kaust.edu.sa/dannp/data.php and https://doi.org/10.5281/zenodo.1001086.

Combined Trajectory Planning and Tracking for Autonomous Vehicles on Deformable Terrains

2020 ◽  
Author(s):  
James Dallas ◽  
Yifan Weng ◽  
Tulga Ersal
Keyword(s):  
Neural Network ◽  
Trajectory Planning ◽  
Autonomous Vehicles ◽  
Performance Metrics ◽  
Soft Soil ◽  
Computation Time ◽  
Operating Conditions ◽  
The Neural Network ◽  
Vehicle Response ◽  
The Impact

Abstract In this work, a novel combined trajectory planner and tracking controller is developed for autonomous vehicles operating on off-road deformable terrains. Common approaches to trajectory planning and tracking often rely on model-dependent schemes, which utilize a simplified model to predict the impact of control inputs to future vehicle response. However, in an off-road context and especially on deformable terrains, accurately modeling the vehicle response for predictive purposes can be challenging due to the complexity of the tire-terrain interaction and limitations of state-of-the-art terramechanics models in terms of operating conditions, computation time, and continuous differentiability. To address this challenge and improve vehicle safety and performance through more accurate prediction of the plant response, in this paper, a nonlinear model predictive control framework is presented that accounts for terrain deformability explicitly using a neural network terramechanics model for deformable terrains. The utility of the proposed scheme is demonstrated on high fidelity simulations for a notional lightweight military vehicle on soft soil. It is shown that the neural network based controller can outperform a baseline Pacejka model based scheme by improving on performance metrics associated with the cost function. In more severe maneuvers, the neural network based controller can achieve sufficient fidelity as compared to the plant to complete maneuvers that lead to failure for the Pacejka based controller. Finally, it is demonstrated that the proposed framework is conducive to real-time implementability.

scholarly journals Language switching training modulates the neural network of non-linguistic cognitive control

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0247100
Author(s):  
Mo Chen ◽  
Fengyang Ma ◽  
Zhaoqi Zhang ◽  
Shuhua Li ◽  
Man Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Cognitive Control ◽  
Structural Equation ◽  
Structural Equation Models ◽  
Brain Regions ◽  
Anterior Cingulate ◽  
Language Switching ◽  
Dorsal Anterior Cingulate Cortex ◽  
The Neural Network ◽  
The Impact

Bilingual language experience, such as switching between languages, has been shown to shape both cognitive and neural mechanisms of non-linguistic cognitive control. However, the neural adaptations induced by language switching remain unclear. Using fMRI, the current study examined the impact of short-term language switching training on the neural network of domain-general cognitive control for unbalanced Chinese-English bilinguals. Effective connectivity maps were constructed by using the extended unified structural equation models (euSEM) within 10 common brain regions involved in both language control and domain-general cognitive control. Results showed that, the dorsal anterior cingulate cortex/pre-supplementary motor area (dACC/pre-SMA) lost connection from the right thalamus after training, suggesting that less neural connectivity was required to complete the same domain-general cognitive control task. These findings not only provide direct evidence for the modulation of language switching training on the neural interaction of domain-general cognitive control, but also have important implications for revealing the potential neurocognitive adaptation effects of specific bilingual language experiences.

scholarly journals Evaluation of VIIRS Neural Network Cloud Detection against Current Operational Cloud Masks

2020 ◽  
Author(s):  
Charles H. White ◽  
Andrew K. Heidinger ◽  
Steven A. Ackerman
Keyword(s):  
Neural Network ◽  
Optical Depth ◽  
Infrared Imaging ◽  
Regional Analysis ◽  
True Positive Rate ◽  
Orthogonal Polarization ◽  
Cloud Detection ◽  
The Neural Network ◽  
Cloud Mask ◽  
The Impact

Abstract. Cloud properties are critical to our understanding of weather and climate variability, but their estimation from satellite imagers is a nontrivial task. In this work, we aim to improve cloud detection which is the most fundamental cloud property. We use a neural network applied to Visible Infrared Imaging Radiometer Suite (VIIRS) measurements to determine whether an imager pixel is cloudy or cloud-free. The neural network is trained and evaluated using four years (2016–2019) of coincident measurements between VIIRS and the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP). We successfully address the lack of sun glint in the collocation dataset with a simple semi-supervised learning approach. The results of the neural network are then compared with two operational cloud masks: the MODIS-VIIRS Continuity Cloud Mask (MVCM) and the NOAA Enterprise Cloud Mask (ECM). We find that the neural network outperforms both operational cloud masks in most conditions examined with a few exceptions. The largest improvements we observe occur during the night over snow or ice covered surfaces in the high latitudes. In our analysis, we show that this improvement is not solely due to differences in optical depth-based definitions of a cloud between each mask. We also analyze the differences in true positive rate between day/night and land/water scenes as a function of optical depth. Such differences are a contributor to spatial artifacts in cloud masking and we find that the neural network is the most consistent in cloud detection with respect to optical depth across these conditions. A regional analysis over Greenland illustrates the impact of such differences and shows that they can result in mean cloud fractions with very different spatial and temporal characteristics.

scholarly journals A Hybrid Swarm Intelligent Neural Network Model for Customer Churn Prediction and Identifying the Influencing Factors

Information ◽  
2018 ◽  
Vol 9 (11) ◽  
pp. 288 ◽  
Author(s):  
Hossam Faris
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Churn Prediction ◽  
Hybrid Swarm ◽  
Customer Churn ◽  
The Neural Network ◽  
Proposed Model ◽  
Telecommunication Companies ◽  
Technique Evaluation ◽  
Imbalanced Class Distribution

Customer churn is one of the most challenging problems for telecommunication companies. In fact, this is because customers are considered as the real asset for the companies. Therefore, more companies are increasing their investments in developing practical solutions that aim at predicting customer churn before it happens. Identifying which customer is about to churn will significantly help the companies in providing solutions to keep their customers and optimize their marketing campaigns. In this work, an intelligent hybrid model based on Particle Swarm Optimization and Feedforward neural network is proposed for churn prediction. PSO is used to tune the weights of the input features and optimize the structure of the neural network simultaneously to increase the prediction power. In addition, the proposed model handles the imbalanced class distribution of the data using an advanced oversampling technique. Evaluation results show that the proposed model can significantly improve the coverage rate of churn customers in comparison with other state-of-the-art classifiers. Moreover, the model has high interpretability, where the assigned feature weights can give an indicator about the importance of their corresponding features in the classification process.

Bolt Tightening Using Impact Wrench Based on Neural Networks

2000 ◽  
Vol 12 (6) ◽  
pp. 706-711
Author(s):  
Toru Fujinaka ◽  
◽  
Hirofumi Nakano ◽  
Michifumi Yoshioka ◽  
Sigeru Omatu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Clamping Force ◽  
The Neural Network ◽  
The Impact

A method for controlling the tightening operation of bolts using an impact wrench is proposed, where the neural network is employed for achieving proper clamping force. The characteristics of the clamping force depend on the kind of work to which bolts are tightened, thus a neural network is used for classification of the work. The clamping force, which can only be measured during the test run, is estimated online, using another neural network. Then appropriate input to the actuator of the impact wrench is determined, based on the estimated value of the clamping force.

scholarly journals End-to-end speech emotion recognition using a novel context-stacking dilated convolution neural network

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Duowei Tang ◽  
Peter Kuppens ◽  
Luc Geurts ◽  
Toon van Waterschoot
Keyword(s):  
Neural Network ◽  
Emotion Recognition ◽  
Speech Signal ◽  
State Of The Art ◽  
Speech Emotion Recognition ◽  
Model Parameters ◽  
Proposed Model ◽  
End To End ◽  
The Impact ◽  
Temporal Dependencies

AbstractAmongst the various characteristics of a speech signal, the expression of emotion is one of the characteristics that exhibits the slowest temporal dynamics. Hence, a performant speech emotion recognition (SER) system requires a predictive model that is capable of learning sufficiently long temporal dependencies in the analysed speech signal. Therefore, in this work, we propose a novel end-to-end neural network architecture based on the concept of dilated causal convolution with context stacking. Firstly, the proposed model consists only of parallelisable layers and is hence suitable for parallel processing, while avoiding the inherent lack of parallelisability occurring with recurrent neural network (RNN) layers. Secondly, the design of a dedicated dilated causal convolution block allows the model to have a receptive field as large as the input sequence length, while maintaining a reasonably low computational cost. Thirdly, by introducing a context stacking structure, the proposed model is capable of exploiting long-term temporal dependencies hence providing an alternative to the use of RNN layers. We evaluate the proposed model in SER regression and classification tasks and provide a comparison with a state-of-the-art end-to-end SER model. Experimental results indicate that the proposed model requires only 1/3 of the number of model parameters used in the state-of-the-art model, while also significantly improving SER performance. Further experiments are reported to understand the impact of using various types of input representations (i.e. raw audio samples vs log mel-spectrograms) and to illustrate the benefits of an end-to-end approach over the use of hand-crafted audio features. Moreover, we show that the proposed model can efficiently learn intermediate embeddings preserving speech emotion information.

scholarly journals A practical demonstration on AMSU retrieval precision for upper tropospheric humidity by a non-linear multi-channel regression method

2005 ◽  
Vol 5 (2) ◽  
pp. 451-459 ◽  
Author(s):  
C. Jiménez ◽  
P. Eriksson ◽  
V. O. John ◽  
S. A. Buehler
Keyword(s):  
Neural Network ◽  
Relative Humidity ◽  
Single Channel ◽  
Weighting Function ◽  
Traditional Approach ◽  
Training Dataset ◽  
The Neural Network ◽  
Radiosonde Station ◽  
Neural Network Algorithm ◽  
The Impact

Abstract. A neural network algorithm inverting selected channels from the Advance Microwave Sounding Unit instruments AMSU-A and AMSU-B was applied to retrieve layer averaged relative humidity. The neural network was trained with a global synthetic dataset representing clear-sky conditions. A precision of around 6% was obtained when retrieving global simulated radiances, the precision deteriorated less than 1% when real mid-latitude AMSU radiances were inverted and compared with co-located data from a radiosonde station. The 6% precision outperforms by 1% the reported precision estimate from a linear single-channel regression between radiance and weighting function averaged relative humidity, the more traditional approach to exploit AMSU data. Added advantages are not only a better precision; the AMSU-B humidity information is more optimally exploited by including temperature information from AMSU-A channels; and the layer averaged humidity is a more physical quantity than the weighted humidity, for comparison with other datasets. The training dataset proved adequate for inverting real radiances from a mid-latitude site, but it is limited by not considering the impact of clouds or surface emissivity changes, and further work is needed in this direction for further validation of the precision estimates.

scholarly journals Spatially-Aware Clustering of Ion Images in Mass Spectrometry Imaging Data Using Deep Learning

2020 ◽  
Author(s):  
Wanqiu Zhang ◽  
Marc Claesen ◽  
Thomas Moerman ◽  
M. Reid Groseclose ◽  
Etienne Waelkens ◽  
...  
Keyword(s):  
Neural Network ◽  
Mass Spectrometry ◽  
Deep Learning ◽  
Mass Spectrometry Imaging ◽  
Spatial Information ◽  
Image Clustering ◽  
Imaging Data ◽  
The Neural Network ◽  
Clustering Quality ◽  
The Impact

AbstractComputational analysis is crucial to capitalize on the wealth of spatio-molecular information generated by mass spectrometry imaging (MSI) experiments. Currently, the spatial information available in MSI data is often under-utilized, due to the challenges of in-depth spatial pattern extraction.The advent of deep learning has greatly facilitated such complex spatial analysis. In this work, we use a pre-trained neural network to extract high-level features from ion images in MSI data, and test whether this improves downstream data analysis. The resulting neural network interpretation of ion images, coined neural ion images, are used to cluster ion images based on spatial expressions.We evaluate the impact of neural ion images on two ion image clustering pipelines, namely DBSCAN clustering, combined with UMAP-based dimensionality reduction, and k-means clustering. In both pipelines, we compare regular and neural ion images from two different MSI datasets. All tested pipelines could extract underlying spatial patterns, but the neural network-based pipelines provided better assignment of ion images, with more fine-grained clusters, and greater consistency in the spatial structures assigned to individual clusters.Additionally, we introduce the Relative Isotope Ratio metric to quantitatively evaluate clustering quality. The resulting scores show that isotopical m/z values are more often clustered together in the neural network-based pipeline, indicating improved clustering outcomes.The usefulness of neural ion images extends beyond clustering towards a generic framework to incorporate spatial information into any MSI-focused machine learning pipeline, both supervised and unsupervised.

scholarly journals Assessment of the impact of government expenditure on environmental protection on the GDP in the context of environmental legislation

2020 ◽  
Vol 7 (3) ◽  
pp. 375-384
Author(s):  
Oksana Levytska ◽  
Aliona Romanova
Keyword(s):  
Neural Network ◽  
Sustainable Development ◽  
Environmental Protection ◽  
Neural Network Model ◽  
Current Problem ◽  
Government Expenditure ◽  
Environmental Legislation ◽  
Environmental Programs ◽  
The Neural Network ◽  
The Impact

This article assesses the impact of government expenditure on environmental protection and various social and economic variables on GDP. It analyzes the environmental legislation necessary for the development of environmental activities if Ukraine. The current problem is determined by reducing government expenditure on environmental protection, which will negatively affect the implementation of environmental protection projects. The result of the study is to clarify the extent to which government expenditure on environmental protection should be modified to increase GDP, which changes should be made to the legislation achieving a transition to economies that guarantee sustainable development. The relationships between the variables were analyzed by making use of the neural network model. The study concludes suggestions on how to increase government expenditure on environmental protection for the coming years to strengthen funding for important environmental programs and to make appropriate amendments to the legislation of Ukraine.

Sign in / Sign up

Export Citation Format

Share Document