Filters








4,260 Hits in 5.5 sec

Automated Optical Multi-layer Design via Deep Reinforcement Learning [article]

Haozhu Wang, Zeyu Zheng, Chengang Ji, L. Jay Guo
2020 arXiv   pre-print
Our algorithm successfully discovered high-performance designs, outperforming structures designed by human experts in task 1, and a state-of-the-art memetic algorithm in task 2.  ...  Optical multi-layer thin films are widely used in optical and energy applications requiring photonic designs. Engineers often design such structures based on their physical intuition.  ...  RELATED WORK Researchers have developed reinforcement learning methods for solving various combinatorial optimization problems.  ... 
arXiv:2006.11940v1 fatcat:t4sjhfgnsvfutmv6o54xcyc6pa

Nature-Inspired Metaheuristic Techniques for Combinatorial Optimization Problems: Overview and Recent Advances

Md Ashikur Rahman, Rajalingam Sokkalingam, Mahmod Othman, Kallol Biswas, Lazim Abdullah, Evizal Abdul Kadir
2021 Mathematics  
A survey of seven different metaheuristic algorithms (which are proposed after 2000) for combinatorial optimization problems is carried out in this study, apart from conventional metaheuristics like simulated  ...  annealing, particle swarm optimization, and tabu search.  ...  Authors also recognize the contribution of the Department of Fundamental and Applied Sciences of the Universiti Teknologi PETRONAS for their invaluable support.  ... 
doi:10.3390/math9202633 fatcat:tk2ymswg4fau3bpx2kxmcmmyoi

OPTIMIZATION METHODS AND HEURISTICS AND THEIR ROLE IN SUPPLY CHAINS AND LOGISTICS [chapter]

Dejan Dragan, Tomaž Kramberger, Vlado Popović
2020 Quantitative Methods in Logistics  
The main goal is to update interested readers about an enormous class of prevailing optimization methods and heuristics that have been designed for solving of numerous types of optimization problems.  ...  In the perspective of actual practice, it is also briefly stressed how and where optimization methods can be effectively applied in the field of supply chains and logistics.  ...  Model-Based Randomized Methods for Global Optimization Quttineh Models and Methods for Costly Global Optimization and Military Decision Support Systems (thesis) Hoffman Combinatorial Optimization: Current  ... 
doi:10.37528/ftte/9786673954196.008 fatcat:2r64lxc7unfedbndot4j5xahqq

A Reinforcement learning method for Optical Thin-Film Design [article]

Anqing Jiang, Liangyao Chen, Osamu Yoshie
2021 arXiv   pre-print
A challenging problem that arises is an automated material search. In this work, we propose a new end-to-end algorithm for optical thin-film inverse design.  ...  The vast majority of this research has focused on the parameter optimization (layer thickness, and structure size) of optical thin-films.  ...  From our search for 1000 epochs, we plot in Fig. 6 (b) the best and cumulative absorption in each epoch.  ... 
arXiv:2102.09398v1 fatcat:k55x4forinevvj2mj5rw25muo4

A Reinforcement Learning Method for Optical Thin-Film Design

Anqing JIANG, Osamu YOSHIE
2022 IEICE transactions on electronics  
A challenging problem that arises is an automated material search. In this work, we propose a new end-to-end algorithm for optical thin-film inverse design.  ...  The vast majority of this research has focused on the parameter optimization (layer thickness, and structure size) of optical thin-films.  ...  For each model, the search process is 1000 epoches. The maximum absorption values discovered by each model are reported in Fig. 7 .  ... 
doi:10.1587/transele.2021ecp5013 fatcat:72ktix26jrdi3oaoijm7b45ake

A comprehensive review of firefly algorithms

Iztok Fister, Iztok Fister, Xin-She Yang, Janez Brest
2013 Swarm and Evolutionary Computation  
The firefly algorithm has become an increasingly important tool of Swarm Intelligence that has been applied in almost all areas of optimization, as well as engineering practice.  ...  On the other hand, it encourages new researchers and algorithm developers to use this simple and yet very efficient algorithm for problem solving.  ...  Using firefly algorithms for combinatorial optimization problems demands a mapping of the discrete variables (usually permutation of integer) in the problem space to continuous variables in the search  ... 
doi:10.1016/j.swevo.2013.06.001 fatcat:szzcix3dlzgljgxnpnqauafmlu

Solving the Tension/Compression Spring Design Problem by an Improved Firefly Algorithm

Yüksel Çelik, Hakan Kutucu
2018 International Workshop on Informatics & Data-Driven Medicine  
The use of meta-heuristics greatly increases the possibility of finding a qualitative solution for complex, combinatorial optimization problems in a reasonable time.  ...  Firefly Algorithm (FA) is a recent one of such meta-heuristic algorithms It is based on a swarm intelligence and inspired by the social behaviors of fireflies.  ...  Introduction The goal of heuristic or metaheuristic algorithms for solving combinatorial optimization problems is to find an optimal value under specified constraints.  ... 
dblp:conf/iddm/CelikK18 fatcat:qp7lh6hj5fbpbhlah6gndfetay

Chemoinformatics and Drug Discovery

Jun Xu, Arnold Hagler
2002 Molecules  
The main data mining approaches used in cheminformatics, such as descriptor computations, structural similarity matrices, and classification algorithms, are outlined.  ...  The applications of cheminformatics in drug discovery, such as compound selection, virtual library generation, virtual high throughput screening, HTS data mining, and in silico ADMET are discussed.  ...  Richard Shaps for his comments and advice.  ... 
doi:10.3390/70800566 fatcat:vsf3iljr45cy3j7qadvq35pbcq

The prediction of human oral absorption for diffusion rate-limited drugs based on heuristic method and support vector machine

H. X. Liu, R. J. Hu, R. S. Zhang, X. J. Yao, M. C. Liu, Z. D. Hu, B. T. Fan
2005 Journal of Computer-Aided Molecular Design  
At the same time, in order to show the influence of different molecular descriptors on absorption and to well understand the absorption mechanism, HM was used to build several multivariable linear models  ...  In addition, this paper provides a new and effective method for predicting the absorption of the drugs from their structures and gives some insight into structural features related to the absorption of  ...  In addition, they are useful in areas like design of virtual compound libraries, computational-chemical optimization of compounds, and design of combinatorial libraries with appropriate ADME (absorption  ... 
doi:10.1007/s10822-005-0095-8 pmid:16059665 fatcat:wlwyaylxrrbbln4emzbjhpvece

Designing Fast Absorbing Markov Chains

Stefano Ermon, Carla Gomes, Ashish Sabharwal, Bart Selman
2014 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
process and fed to a gradient-based optimization package.  ...  Markov Chains are a fundamental tool for the analysis of real world phenomena and randomized algorithms.  ...  Acknowledgments This research is funded by NSF Expeditions in Computing grant #0832782 and Computing Research Infrastructure grant #1059284.  ... 
doi:10.1609/aaai.v28i1.8843 fatcat:pux3d3v54beujc4sohac52uddm

A new selection operator to improve the performance of genetic algorithm for optimization problems

Amarita Ritthipakdee, Arit Thammano, Nol Premasathian, Bunyarit Uyyanonvara
2013 2013 IEEE International Conference on Mechatronics and Automation  
Nature-inspired algorithms, such as Particle swarm optimization (PSO), Ant colony optimization (ACO), and Firefly algorithm, are well known for solving NP-hard optimization problems.  ...  They are capable of obtaining optimal solutions in a reasonable time. The algorithm presented in this paper is a combination of a firefly mating concept and genetic algorithm.  ...  Our proposed model is based on a combination of a firefly mating concept and genetic algorithm (GA).  ... 
doi:10.1109/icma.2013.6617947 fatcat:b6ghzqj53fgvvc5phtdz4c3dxe

Book announcements

1991 Discrete Applied Mathematics  
Wallen, Automated Proof Search in Non-Classical Logics (MIT Press, Cambridge, MA, 1990) 239 pages tive simulation algorithm. Implementation of the simulation algorithm.  ...  Rules in the model). Chapter 3: Model Interpretation and Derivation of Surface Knowledge. Formalizaknowledge base. Chapter 4: Know/edge Base Compression by Means of Machine Learning.  ...  Chapter 1: Proof Search in Classical Sequent Calculi. Syntax  ... 
doi:10.1016/0166-218x(91)90059-6 fatcat:h2qaplcx7zg3xneksfm2e4gstq

Inverse Design of Composite Metal Oxide Optical Materials based on Deep Transfer Learning [article]

Rongzhi Dong, Yabo Dan, Xiang Li, Jianjun Hu
2020 arXiv   pre-print
Our approach is based on the combination of a deep neural network model and global optimization algorithms including a genetic algorithm and Bayesian optimization.  ...  Herein we propose TLOpt, a transfer learning based inverse optical materials design algorithm for suggesting material compositions with a desired target light absorption spectrum.  ...  Acknowledgement Research reported in this work was supported in part by NSF under grant and 1940099 and 1905775 and by NSF SC EPSCoR Program under award number (NSF Award OIA-1655740 and GEAR-CRP 19-GC02  ... 
arXiv:2008.10618v1 fatcat:eai6brsdkzdtjf7ha3lwe5vkjm

A Hybrid Firefly Algorithm Approach for Job Shop Scheduling Problem

Gayathri Devi K
2021 International Journal for Research in Applied Science and Engineering Technology  
Abstract: Job shop scheduling has always been one of the most sought out research problems in Combinatorial optimization. Job Shop Scheduling problems (JSSP) are categorized under NP hard problems.  ...  The hybrid technique has the advantages of all three algorithms and are combined in such a way that a quicker and better optimal solution is obtained.  ...  BIBLIOGRAPHY [1] Crama Y (1997) Combinatorial optimization models for production scheduling in automated manufacturing systems. Eur J Oper Res 99:136–153.  ... 
doi:10.22214/ijraset.2021.39536 fatcat:vpxscj5vp5eldfstysw7hh376i

Virtual combinatorial chemistry and in silico screening: Efficient tools for lead structure discovery?

Thierry Langer, G. Wolber
2004 Pure and Applied Chemistry  
Additionally, a new approach for structure-based high-throughput pharmacophore model generation is presented.  ...  In this article, an overview of the most common ligand-based in silico screening techniques is given together with an example on the recent successful application of combined use of pharmacophore modeling  ...  on self-organizing maps for the design of natural product-based combinatorial libraries.  ... 
doi:10.1351/pac200476050991 fatcat:76btyuonb5doneewgh7yrcholy
« Previous Showing results 1 — 15 out of 4,260 results