Filters








34 Hits in 7.3 sec

A Novel Recurrent Adaptive Backstepping Optimal Control Strategy for a Single Inverted Pendulum System [article]

Mohammad Sarbaz
2021 arXiv   pre-print
By this method, an inverted pendulum is stabilized using projection recurrent neural network-based adaptive backstepping control (PRNN-ABC).  ...  The inverted pendulum is a popular nonlinear system that is used in both industry and academic and is applied various control approaches since it has many applications.  ...  Therefore, to solve this problem, an optimal backstepping control approach based on projection recurrent neural network is studied in this work for inverted pendulum.  ... 
arXiv:2110.09846v1 fatcat:lvulahp355cx7a23gjimodepey

Bilevel methods for image reconstruction [article]

Caroline Crockett, Jeffrey A. Fessler
2021 arXiv   pre-print
We then turn to ways to optimize the bilevel problem, providing pros and cons of the variety of proposed approaches. Finally we overview bilevel applications in image reconstruction.  ...  One can view the bilevel problem as formalizing hyperparameter optimization, as bridging machine learning and cost function based optimization methods, or as a method to learn variables best suited to  ...  Acknowledgements 80 Acknowledgements This work was made possible in part due to the support of NIH grant R01 EB023618, NSF grant IIS 1838179, and the Rackham Predoctoral Fellowship.  ... 
arXiv:2109.09610v1 fatcat:lfr5e2posbe43otwvgqjn5xhiq

Deep Declarative Networks: A New Hope [article]

Stephen Gould, Richard Hartley, Dylan Campbell
2020 arXiv   pre-print
Specifically, the forward function is implicitly defined as the solution to a mathematical optimization problem.  ...  We also provide numerous insights and illustrative examples of declarative nodes and demonstrate their application for image and point cloud classification tasks.  ...  ACKNOWLEDGMENTS We give warm thanks to Bob Williamson and John Lloyd for helpful discussions, and anonymous reviewers for insightful suggestions.  ... 
arXiv:1909.04866v2 fatcat:rhvrnldiojcbjnkuj6arsi67a4

Tutorial on amortized optimization for learning to optimize over continuous domains [article]

Brandon Amos
2022 arXiv   pre-print
Optimization is a ubiquitous modeling tool and is often deployed in settings which repeatedly solve similar instances of the same problem.  ...  learning, convex optimization, and deep equilibrium networks.  ...  Atlas Wang for insightful discussions and feedback on this tutorial.  ... 
arXiv:2202.00665v2 fatcat:tvgy2hp2i5f23cwbhuoex3gw2m

Solving inverse problems using data-driven models

Simon Arridge, Peter Maass, Ozan Öktem, Carola-Bibiane Schönlieb
2019 Acta Numerica  
The focus is on solving ill-posed inverse problems that are at the core of many challenging applications in the natural sciences, medicine and life sciences, as well as in engineering and industrial applications  ...  Recent research in inverse problems seeks to develop a mathematically coherent foundation for combining data-driven models, and in particular those based on deep learning, with domain-specific knowledge  ...  Acknowledgements This article builds on lengthy discussions and long-standing collaborations with a large number of people.  ... 
doi:10.1017/s0962492919000059 fatcat:2f7te542wrftphdhurcdnw6dqu

On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks [article]

Jeremias Sulam, Aviad Aberdam, Amir Beck, Michael Elad
2018 arXiv   pre-print
We explore different iterative methods to solve this new problem in practice, and we propose a new Multi-Layer Iterative Soft Thresholding Algorithm (ML-ISTA), as well as a fast version (ML-FISTA).  ...  We further show how these algorithms effectively implement particular recurrent convolutional neural networks (CNNs) that generalize feed-forward ones without introducing any parameters.  ...  recurrent neural networks.  ... 
arXiv:1806.00701v5 fatcat:hj5nar6whbf73edlehvn2zgmem

Challenges in the Application of Mathematical Programming in the Enterprise-wide Optimization of Process Industries

Ignacio E. Grossmann
2014 Теоретические основы химической технологии  
Recurrent neural networks offer a framework for modelling temporal developments. Causality explains the present state of a system by features, which are prior to the current state.  ...  The problem is solved using a combination of a multi-stage stochastic linear programming (SLP) model and stochastic optimal control, such that the practical application is emphasized.  ...  of concepts and terms in administration Erwin Reizes TD-42 Tuesday, 14:30-16:00 BW-Amber Advances in Stochastic Modeling and Simulation Chair: Basak Tanyeri -A Comparison of Artificial Neural Network  ... 
doi:10.7868/s0040357114050054 fatcat:kli7aeuyxbaplfhup2t6nmuyxq

Challenges in the application of mathematical programming in the enterprise-wide optimization of process industries

Ignacio E. Grossmann
2014 Theoretical foundations of chemical engineering  
Recurrent neural networks offer a framework for modelling temporal developments. Causality explains the present state of a system by features, which are prior to the current state.  ...  The problem is solved using a combination of a multi-stage stochastic linear programming (SLP) model and stochastic optimal control, such that the practical application is emphasized.  ...  of concepts and terms in administration Erwin Reizes TD-42 Tuesday, 14:30-16:00 BW-Amber Advances in Stochastic Modeling and Simulation Chair: Basak Tanyeri -A Comparison of Artificial Neural Network  ... 
doi:10.1134/s0040579514050182 fatcat:3ra5yqooyzgmroo5qccbnauftm

Support Vector Machine Methods and Artificial Neural Networks Used for the Development of Bankruptcy Prediction Models and their Comparison

Jakub Horak, Jaromir Vrbka, Petr Suler
2020 Journal of Risk and Financial Management  
The model of Support Vector Machine shows a relatively high accuracy, but it is not applicable in the structure of correct classifications.  ...  The objective of this paper is to create a model for predicting potential bankruptcy of companies using suitable classification methods, namely Support Vector Machine and artificial neural networks, and  ...  Many SVM algorithms include solving of convex problems, such as linear programming, quadratic programming, as well as nonconvex and more general problems with optimization, such as integer programming,  ... 
doi:10.3390/jrfm13030060 fatcat:77iyg3gcvnh3fnlulk3x5nlzj4

2020 Index IEEE Transactions on Cybernetics Vol. 50

2020 IEEE Transactions on Cybernetics  
., and Gao, H., Reference Trajectory Reshaping Optimi-zation and Control of Robotic Exoskeletons for Human-Robot Co-Manipulation; TCYB Aug. 2020 3740-3751 Wu, X., Jiang, B., Yu, K., Miao, c., and Chen,  ...  ., +, TCYB Dec. 2020 4862-4875 Convergence of numerical methods A Finite-Time Convergent and Noise-Rejection Recurrent Neural Network and Its Discretization for Dynamic Nonlinear Equations Solving.  ...  ., +, TCYB June 2020 2803-2813 Finite difference methods A Finite-Time Convergent and Noise-Rejection Recurrent Neural Network and Its Discretization for Dynamic Nonlinear Equations Solving.  ... 
doi:10.1109/tcyb.2020.3047216 fatcat:5giw32c2u5h23fu4drupnh644a

The Vessel Schedule Recovery Problem (VSRP) – A MIP model for handling disruptions in liner shipping

Berit D. Brouer, Jakob Dirksen, David Pisinger, Christian E.M. Plum, Bo Vaaben
2013 European Journal of Operational Research  
We illustrate the application of these ideas in four major problems: a) integration of planning and scheduling in batch processes that lead to large-scale mixed-integer linear programs, b) optimization  ...  The problem is framed as a multi-indicator assessment and is solved using a minimal cost objective.  ...  -Optimal Dynamic Tax Evasion: A Portfolio Approach Francesco Menoncin, Economics, Brescia University, Via S. Faustino, 74/B, 25122, Brescia, Italy, menoncin@eco.unibs.it, Rosella Levaggi  ... 
doi:10.1016/j.ejor.2012.08.016 fatcat:c27kagfnxnhjfbil2rydhjhomm

Decentralized Safe Multi-agent Stochastic Optimal Control using Deep FBSDEs and ADMM [article]

Marcus A. Pereira, Augustinos D. Saravanos, Oswin So, Evangelos A. Theodorou
2022 arXiv   pre-print
Specifically, we propose a Merged CADMM-OSQP implicit neural network layer, that solves a mini-batch of both, local quadratic programs as well as the overall consensus problem, as a single optimization  ...  Safety is mathematically encoded using stochastic control barrier functions and safe controls are computed by solving quadratic programs.  ...  Augustinos Saravanos acknowledges financial support by the A. Onassis Foundation Scholarship.  ... 
arXiv:2202.10658v1 fatcat:jrilskgy2rg57fchspzvilnj7m

A General Descent Aggregation Framework for Gradient-based Bi-level Optimization [article]

Risheng Liu, Pan Mu, Xiaoming Yuan, Shangzhi Zeng, Jin Zhang
2022 arXiv   pre-print
In recent years, a variety of gradient-based methods have been developed to solve Bi-Level Optimization (BLO) problems in machine learning and computer vision areas.  ...  in real-world applications.  ...  They can be identified as a new iterative optimization scheme for solving the simple bi-level problem without the UL strong convexity.  ... 
arXiv:2102.07976v3 fatcat:jsstcp5nlvez3d6vh7st4bzjgi

Visible Light-Assisted Soft-Chemistry Route to Silver Nanomaterials at Room Temperature

Yi Wu, Xin Liu, Zi Huang, Xiang Fei He, Xi Yang, Qing Li
2019 Key Engineering Materials  
Silver nanoparticles (AgNPs) were synthesizd by a light-assisted liquid phase reduction method with sodium hypophosphite as a reducing agent. DTAB was used to perform as the surfactant.  ...  AgNPs were characterized with powder X-ray diffraction (XRD) and scanning electron microscope (SEM). The result showed that the nanoparticles are spherical and cube.  ...  As a solution method for linear or convex optimization problems, it is possible to apply mathematical solution methods finding an exact optimal solution such as the simplex method, the successive quadratic  ... 
doi:10.4028/www.scientific.net/kem.807.165 fatcat:xara5sxzf5fsvbib2dy6vrl7j4

Microgrid management with weather-based forecasting of energy generation, consumption and prices [article]

Jonathan Dumas
2021 arXiv   pre-print
in energy applications.  ...  Most of the generation technologies based on renewable sources are non-dispatchable, and their production is stochastic and complex to predict in advance.  ...  A novel pooling-based deep recurrent neural network is proposed by Shi et al. [158] in the field of short-term household load forecasting.  ... 
arXiv:2107.01034v7 fatcat:c5a7d2w2uzez3par3q6gs3elaq
« Previous Showing results 1 — 15 out of 34 results