The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
Couellan, Neural network training via quadratic programming (123-139); Ohseok Kwon, Bruce Golden and Ed- ward Wasil, A neural network model for predicting Atlantic hurricane activity (141-151); Jeffery ... , Using metaheuristics in multiobjective resource constrained project scheduling (359-374); Federico Della Croce, Jatinder N. ...
Advances in Reinforcement Learning
Present the three-layer feed-forward neural networks, use the samples acquired in simulation to weight-train the neural network to approach the stochastic functions in model (5) . ... There are a lot of complex calculations for probabilities of stochastic variables in model (5) , as for the complexity of multi-priorities scheduling, even a schedule sequence is determined, the stochastic ... A set of chapters in this book provide a general overview of RL while other chapters focus mostly on the applications of RL paradigms: Game Theory, Multi-Agent Theory, Robotic, Networking Technologies, ...doi:10.5772/13195 fatcat:6rfzylvckvghzdhupi4keytpz4
The Journal of Business
‘Optimal Design and Manage- ment of Local Access Networks.”’ Balasubramanian Rangaswamy. Univ. Colorado. ‘‘Multiple Resource Planning and Allocation in Resource-Constrained Project Networks.” ... “‘Neural Network Models Using a Genetic Algo- rithm to Perform the Function of X-Bar Charts.” Rajan Kumaralingam. Alabama. ...
A brief survey of neurophysiology. Learning and memory: a summary of experimental observations. Chapter 3: The Dynamics of Neural Networks: A Stochastic Approach. Introducing the problem. ... Stochastic Hebbian neural networks in the limit of finite numbers of memorized patterns. Storing an infinite number of patterns in stochastic Hebbian networks: the technique of field distributions. ...doi:10.1016/0166-218x(93)90109-2 fatcat:selkadhvzrfs5mcrv2jqauh5wm
In this research, A Potts mean field feedback artificial neural network algorithm is developed and explored for the multiobjective resource constrained project scheduling problem. ... To overcome this deficiency, a Potts mean field feedback artificial neural network is designed and integrated into the scheduling scheme so as to automatically select the suitable activity for each stage ... of much inspiration for neural network studies. ...doi:10.22436/jmcs.09.03.07 fatcat:f5dx7hhrjvd3fjdjmncorp6tyq
Efficient scheduling of application tasks in such environments is challenging due to constrained resource capabilities, mobility factors in IoT, resource heterogeneity, network hierarchy, and stochastic ... Thus, we propose an A3C based real-time scheduler for stochastic Edge-Cloud environments allowing decentralized learning, concurrently across multiple agents. ... ACKNOWLEDGEMENTS This research work is supported by the Melbourne-Chindia Cloud Computing (MC3) Research Network and the Australian Research Council. ...doi:10.1109/tmc.2020.3017079 fatcat:ubmsvqg5anfplaaiovazrijp4a
In order to solve these models, stochastic simulation, neural network and genetic algorithm are integrated to produce a hybrid intelligent algorithm. ... The expected value model and the chance-constrained programming model for unbalanced bidding problem are established on the condition that quantities of each activity are stochastic variables and the total ... Then stochastic simulation, neural network and genetic algorithm will be integrated to produce a hybrid intelligent algorithm for solving these models. ...doi:10.5539/cis.v2n1p188 fatcat:my6pgtcqwfcmbcwm3tk47k6ere
Conducted experiments on the constrained Job Shop and Resource Allocation problems prove the superiority of the proposal for computing rapid solutions when compared to classical heuristic, metaheuristic ... This paper presents a framework to tackle constrained combinatorial optimization problems using deep Reinforcement Learning (RL). ... As argued in this work, a single neural network is employed to learn a policy π θ that acts as an heuristic for solving constrained combinatorial problems. ...arXiv:2006.11984v1 fatcat:cp3mnl5tkrdhvfjobkckspgngi
2006 IEEE International Conference on Cluster Computing
Precedence- Constrained Parallel Tasks on Clusters Qin, Xiao Stochastic Scheduling with Availability Constraints in Heterogeneous Clusters Raisch, Christoph Improving Communication Performance ... Strategies for Scheduling Precedence- Constrained Parallel Tasks on Clusters Workshop on High-Performance I/O Techniques and ...doi:10.1109/clustr.2006.311921 fatcat:vmbbimypuze7ncjqfonu4po5l4
optimization, particle swarm optimization, neural network, simulated annealing, genetic algorithm, and hybrid methods. ... Some of the papers are dedicated to the development of advanced optimization methods for direct or indirect use in engineering problems such as network, scheduling, production planning, industrial engineering ... Khalilzadeh et al. introduces a multimode resource-constrained project scheduling problem with finish-to-start precedence relations among project activities, considering renewable and nonrenewable resource ...doi:10.1155/2012/759548 fatcat:3wkb26nllfgp7hf347b3eoox4y
The Journal of Business
‘‘Scheduling Procedures in a Constrained Multiple Resource Dynamic Shop Environment with Stochastic Activity Times.”’ Sherry Bowman. Pennsylvania State. ‘‘Cooperative Buyer-Supplier Relation- ships.” ... ‘‘Neural Network Models for Optimization and Prediction: Algorithms and Applications.’ Jing Li. Oklahoma State. ...
Alexandrov and Yuri Kochetov, Behavior of the ant colony algorithm for the set covering problem (255-260); Lutz Beinsen and Martin Kithrer, Comparison of exchange rate fore- casts by neural networks and ... A. Yanushke- vich, Scheduling with deadlines and nested processing intervals for a single machine (378-382); Jatinder N. D. ...
A variety of approaches have been developedto solve the problem of dynamic scheduling. ... flexibility and robustness, and to suggest variousorientations for further work is this area of research. ... In this works a neural network approach was proposed to a dynamic job shop scheduling problems. ...doi:10.6084/m9.figshare.7379393 fatcat:fcdzn7qcpva2lpvzd6kkhxftfu
K eyw ords scheduling, neural networks A bstract. Arti® cial neural networks ( ANNs) attempt to emulate the massively parallel and distributed processing of the human brain. ... The objective is to review the entire literature of neural networks that are applied to various scheduling problems ranging from a single machine scheduling to satellite broadcasting scheduling. ... In another study, Vaithyanathan and I gnizo ( 1992) developed a stochastic neural network to solve resource constrained scheduling models. ...doi:10.1080/095372898234460 fatcat:2qhpesl3crao3nnrx56h5agn4i
Resource-efficient convolution neural networks enable not only the intelligence on edge devices but also opportunities in system-level optimization such as scheduling. ... In this work, we aim to improve the performance of resource-constrained filter pruning by merging two sub-problems commonly considered, i.e., (i) how many filters to prune for each layer and (ii) which ... resource constraints without having to search for and train a network for a long time. ...arXiv:1810.00518v2 fatcat:yk7l2fflxbejfoshmxqumzmzfm
« Previous Showing results 1 — 15 out of 8,031 results