418,684 Hits in 3.9 sec

Model Inversion Networks for Model-Based Optimization [article]

Aviral Kumar, Sergey Levine
2019 arXiv   pre-print
We propose to address such problem with model inversion networks (MINs), which learn an inverse mapping from scores to inputs.  ...  We evaluate MINs on tasks from the Bayesian optimization literature, high-dimensional model-based optimization problems over images and protein designs, and contextual bandit optimization from logged data  ...  We thank anonymous reviewers for feedback on an earlier version of this paper.  ... 
arXiv:1912.13464v1 fatcat:gv2w5ebrxjhhzodlfu5ppddca4

Inverse Optimization based Detection of Leaks from Simulated Pressure in Water Networks, Part 1: Analysis for a Single Leak

Peace K. Amoatey, University of Ghana, András Bárdossy, Heidrun Steinmetz, Universität Stuttgart (ISWA), University of Kaiserslautern
2018 Journal of Water Management Modeling  
The model works very well in detecting leaks occurring in a gridded network while it performs below average for leaks occurring in branched areas.  ...  A minimum of eight reference points is required for a leak to be detected in any part of the network.  ...  Jasper et al. (2013) used simulation-optimization inverse modeling to detect leaks in the water network.  ... 
doi:10.14796/jwmm.c460 fatcat:hh3ohqwmova4xhaagq7vtbmt5e

Inverse Optimization based Detection of Leaks from Simulated Pressure in Water Networks, Part 2: Analysis for Two Leaks

Peace K. Amoatey, University of Ghana, András Bárdossy, Heidrun Steinmetz, Universität Stuttgart (ISWA), University of Kaiserslautern
2018 Journal of Water Management Modeling  
An optimization-based approach is used to model leakage detection in water networks from simulated network pressures.  ...  The model detects leaks using the optimization functions for which the sum of squared errors (SSE) is equal to zero.  ...  Iddi of the University of Ghana assisted in the mathematical notation of the model. I am highly indebted to Professors Steinmetz and Bárdossy for their guidance during my PhD studies.  ... 
doi:10.14796/jwmm.c461 fatcat:5f4bu4cknvb55cxqaitvcy57lq

RBF Neural Network-Based Prediction and Inverse Calculation of Air Pollutant Emission Concentration

Zheng Xipeng
2018 American Journal of Biological and Environmental Statistics  
A data prediction model for RBF neural network was created.  ...  According to the measured values and the predicted data, Gaussian plume diffusion model for air pollution was created, and the quadratic optimization model and inversion method for inverse calculation  ...  The Gaussian plume diffusion model-based experimental data were used to create a neural network model.  ... 
doi:10.11648/j.ajbes.20180402.13 fatcat:zmqrphynave5tjr7gpl4woftkm

Sparse Network Inversion for Key Instance Detection in Multiple Instance Learning [article]

Beomjo Shin, Junsu Cho, Hwanjo Yu, Seungjin Choi
2020 arXiv   pre-print
The main idea is to use the neural network inversion to find which instances made contribution to the bag-level prediction produced by the trained MIL model.  ...  Moreover, we incorporate a sparseness constraint into the neural network inversion, leading to the sparse network inversion which is solved by the proximal gradient method.  ...  Neural Network Inversion Neural network inversion is a method that optimizes the input to fit the criterion of the neural network model.  ... 
arXiv:2009.02909v2 fatcat:ahjthzdepnfilacnkfoappk3ha

Remote Sensing Inversion of Suspended Matter Concentration Using a Neural Network Model Optimized by the Partial Least Squares and Particle Swarm Optimization Algorithms

Qiaozhen Guo, Huanhuan Wu, Huiyi Jin, Guang Yang, Xiaoxu Wu
2022 Sustainability  
The inversion accuracy of the optimized neural network model is compared with that of the partial least squares model and the traditional neural network model by determining the coefficient, the mean absolute  ...  The particle swarm optimization algorithm optimizes the weights and thresholds of the neural network model and it thus effectively overcomes the over-fitting of the neural network.  ...  It developed an optimized neural network model based on the partial least squares algorithm and the particle swarm optimization algorithm, the PLS-PSO-BPNN model and used the measured suspended matter  ... 
doi:10.3390/su14042221 fatcat:cfzjzaibrbgetl6xbdviy5emie

Integrating Deep Neural Networks with Full-waveform Inversion: Reparametrization, Regularization, and Uncertainty Quantification [article]

Weiqiang Zhu, Kailai Xu, Eric Darve, Biondo Biondi, Gregory C. Beroza
2021 arXiv   pre-print
We propose a neural-network-based full waveform inversion method (NNFWI) that integrates deep neural networks with FWI by representing the velocity model with a generative neural network.  ...  Full-waveform inversion (FWI) is an accurate imaging approach for modeling velocity structure by minimizing the misfit between recorded and predicted seismic waveforms.  ...  We ran 100 Monte Carlo samplings based on the optimized neural network model to calculate the standard deviation of the sampled velocity models.  ... 
arXiv:2012.11149v3 fatcat:iptj2ibv7ndaxfwa3nzsp2dq7u

Hybrid Neural Network Controller Design for a Batch Reactor to Produce Methyl Methacrylate

Paisan Kittisupakorn, Thanutchaporn Charoenniyom, Wachira Daosud
2014 Engineering Journal  
Keywords: Methyl methacrylate, batch reactor, neural network based model predictive control, neural network direct inverse control, dynamic optimization.  ...  To control the temperature, neural network based control approaches: a neural network direct inverse control (NNDIC) and a neural network based model predictive control (NNMPC) have been formulated.  ...  An optimal neural network structures for forward and inverse models are chosen based on mean square error (MSE).  ... 
doi:10.4186/ej.2014.18.1.145 fatcat:d5qhxmftrndivlrtefiwj42umm

Review Article: Model Meets Deep Learning in Image Inverse Problems

Na Wang & Jian Sun
2020 CSIAM Transactions on Applied Mathematics  
In this paper, we will review a new trend of methods for image inverse problem that combines the imaging/degradation model with deep learning approach.  ...  These methods are typically designed by unrolling some optimization algorithms or statistical inference algorithms into deep neural networks.  ...  Other related research The above mentioned model-driven deep learning networks are based on statistical and optimization models.  ... 
doi:10.4208/csiam-am.2020-0016 fatcat:peaina2vorg23ow5seswsi7pzu

Microwave Lna Design Based On Adaptive Network Fuzzy Inference And Evolutionary Optimization

Samad Nejatian, Vahideh Rezaie, Vahid Asadpour
2010 Zenodo  
This paper presents a novel approach for the design of microwave circuits using Adaptive Network Fuzzy Inference Optimizer (ANFIO).  ...  The method takes advantage of direct synthesis of subsections of the amplifier using very fast and accurate ANFIO models based on exact simulations using ADS.  ...  Two optimization methodologies based on inverse modeling and space mapping are examined. ANFIS model and NN model are used for each method. A.  ... 
doi:10.5281/zenodo.1083339 fatcat:pie4bjrbi5azdhk67eacvlwkoy

Latent Vector Recovery of Audio GANs [article]

Andrew Keyes, Nicky Bayat, Vahid Reza Khazaie, Yalda Mohsenzadeh
2020 arXiv   pre-print
To accommodate for the lack of an original latent vector for real audio, we optimize the residual network on the perceptual loss between the real audio samples and the reconstructed audio of the predicted  ...  Through our deep neural network based method of training on real and synthesized audio, we are able to predict a latent vector that corresponds to a reasonable reconstruction of real audio.  ...  Acknowledgements The authors would like to thank Western BrainsCAN for the generous support of this research. The study was conducted on Compute Canada resources.  ... 
arXiv:2010.08534v1 fatcat:sdtaedxb6faqfoyh3wfc5d6kua

A physics-based neural-network way to perform seismic full waveform inversion

Yuxiao Ren, Xinji Xu, Senlin Yang, Lichao Nie, Yangkang Chen
2020 IEEE Access  
Thus, following the procedures of traditional seismic full waveform inversion, we propose a seismic waveform inversion network, namely SWINet, based on wave-equation-based forward modeling network cells  ...  differentiation, Adam optimizer and mini-batch strategy, etc.  ...  FIGURE 4 . 4 The network architecture of the seismic waveform inversion network SWINet based on nt forward modeling cells.  ... 
doi:10.1109/access.2020.2997921 fatcat:cu7dch7w3zge7pdtmps5eocy6y

Optimized direct inverse control to control altitude of a small helicopter

Herwin Suprijono, Wahidin Wahab, Benyamin Kusumoputro, P. Tandon, M. Guo
2015 MATEC Web of Conferences  
By using a real small helicopter TREX 450, the neural network based DIC model was performed with an acceptable of error, however, in order to have a better performance, an optimized neural network DIC  ...  The experiment results show that the optimized neural networks DIC model have a better performance with lower total error rate compare with that of the un-optimized neural networks DIC model.  ...  Neural network direct inverse control (NN-DIC) The NN-DIC algorithm is a novel concept based on the Neural Networks control using the inverse of the plant as the model of controller.  ... 
doi:10.1051/matecconf/20153404004 fatcat:ao22uhplarbwrdjtfbdn7cchei

Structural control using magnetorheological dampers governed by predictive and dynamic inverse models

Luis Augusto Lara Valencia, José Luis Vital-de Brito, Yamile Valencia-Gonzalez
2014 Dyna  
necessary optimal control forces and the voltages required for the development of these forces through a prediction model and an inverse model, which are pioneers in this kind of systems.  ...  The results obtained show that the control design based on neural networks that was developed in the present study is a reliable and efficient, achieving reductions of up to 69% for the peak response value  ...  Scientific and Technological Development (Conselho Nacional de Desenvolvimento Científico e Tecnológico -CNPq) for the development of the present study.  ... 
doi:10.15446/dyna.v81n188.41774 fatcat:y2rul4qyp5g2pabigjcg6txrsu

Leak Detection through Hydraulic Transient Analysis [chapter]

Lennart Jönsson, Magnus Larson
1992 Fluid Mechanichs and its Application  
Uniquely, it contains information for over 95 publications in a tabular form, presenting domain type, analysis approach, optimization technique, topographic complexity of the case study, leak unknowns  ...  This paper presents a literature review on major aspects of hydraulic transient-based leak detection in pipe systems over the past three decades.  ...  Torres, Besançon [16] Title: Multi-leak estimator for pipelines based on an orthogonal collocation model Analysis approach: Hydraulic modeling Optimization Technique: N/A Domain: Time Network  ... 
doi:10.1007/978-94-017-2677-1_22 fatcat:n46n56kz6zeldaahs2rqei2pnu
« Previous Showing results 1 — 15 out of 418,684 results