48,943 Hits in 5.4 sec

Adapting Convergent Scheduling Using Machine-Learning [chapter]

Diego Puppin, Mark Stephenson, Saman Amarasinghe, Martin Martin, Una-May O'Reilly
2004 Lecture Notes in Computer Science  
Because of this, a convergent scheduler is presented with a vast number of legal pass orderings. In this work, we use machine-learning techniques to automatically search for good orderings.  ...  Convergent scheduling is a general framework for instruction scheduling and cluster assignment for parallel, clustered architectures.  ...  This paper builds upon it by using machine learning techniques to automatically find good orderings for a convergent scheduler.  ... 
doi:10.1007/978-3-540-24644-2_2 fatcat:mutyd35akbbizam7n4i6lgbuf4

A job-shop scheduling method based on multi-agent immune algorithm

Xinli Xu, Ping Hao, Wanliang Wang
2009 2009 Chinese Control and Decision Conference  
Combining the intelligent ant and reinforcement learning, an on-line job-shop scheduling model based on the adaptive agent was proposed.  ...  When the production environment changed, e.g. the machines or the orders were changed, the adaptive agent could make an adjustment and the optimal assignment of resources could be realized finally.  ...  Now in the research of multi-agent technology and its applications to the scheduling, there are dynamic job-shop scheduling using reinforcement learning agents [4] , dynamic scheduling and rescheduling  ... 
doi:10.1109/ccdc.2009.5191798 fatcat:fhe2kpyerne7rcqmong5w5lh34

A Novel Learning Rate Schedule in Optimization for Neural Networks and It's Convergence

Jieun Park, Dokkyun Yi, Sangmin Ji
2020 Symmetry  
Numerical experiments demonstrate that learning is good effective when using the proposed learning rate schedule in various situations.  ...  The process of machine learning is to find parameters that minimize the cost function constructed by learning the data.  ...  Currently, adaptive optimization methods and adaptive learning rate schedules are used in combination.  ... 
doi:10.3390/sym12040660 fatcat:kzljhb7blve53a3lkwrrpuq4ly

Improved Adaptive Mixture Learning for Robust Video Background Modeling

Dar-Shyang Lee
2002 IAPR International Workshop on Machine Vision Applications  
In this report, we utilize an adaptive learning rate schedule to achieve fast convergence while maintaining adaptability of the model after convergence.  ...  Experimental results show a dramatic improvement in modeling accuracy using an adaptive learning schedule.  ...  We utilize an adaptive learning rate schedule to achieve fast convergence while maintaining model adaptability after convergence.  ... 
dblp:conf/mva/Lee02 fatcat:hbs3qgh2yjgujaux4ptavtlvh4

Learning-based adaptive dispatching method for batch processing machines

Long Chen, Hui Xu, Li Li, Lu Chen
2013 2013 Winter Simulations Conference (WSC)  
This study aims to solve the scheduling problem of batch processing machines (BPMs) in semiconductor manufacturing by using a learning-based adaptive dispatching method (LBADM).  ...  First, an adaptive ant system algorithm (AAS) is proposed to solve the scheduling problem of BPMs according to their characteristics.  ...  The proper use of the intelligent algorithm in batch processing scheduling can significantly improve the scheduling result. Figure 7 shows the convergence of adaptive ant colony algorithm.  ... 
doi:10.1109/wsc.2013.6721735 dblp:conf/wsc/ChenXLC13 fatcat:xc4i5iqnwna7de3fjvytby2goy

Optimal Tracking Current Control of Switched Reluctance Motor Drives Using Reinforcement Q-learning Scheduling [article]

Hamad A. Alharkan, Sepehr Saadatmand, Mehdi Ferdowsi, Pourya Shamsi
2020 arXiv   pre-print
In this paper, a novel Q-learning scheduling method for the current controller of switched reluctance motor (SRM) drive is investigated.  ...  to track the reference current trajectory by scheduling infinite horizon linear quadratic trackers (LQT) handled by Q-learning algorithms.  ...  Fig 5 . 5 The convergence of the gains K values throughout learning process. Fig 6 . 6 The optimal phase voltage introduced to the machine throughout learning.  ... 
arXiv:2006.07764v1 fatcat:33oaqibxcnaf5mm3kmomlzenxi

Adaptive Methods for Nonconvex Optimization

Manzil Zaheer, Sashank J. Reddi, Devendra Singh Sachan, Satyen Kale, Sanjiv Kumar
2018 Neural Information Processing Systems  
Furthermore, we provide a new adaptive optimization algorithm, YOGI, which controls the increase in effective learning rate, leading to even better performance with similar theoretical guarantees on convergence  ...  Extensive experiments show that YOGI with very little hyperparameter tuning outperforms methods such as ADAM in several challenging machine learning tasks.  ...  in many state-of-the-art machine learning models.  ... 
dblp:conf/nips/ZaheerRSKK18 fatcat:lyu6nebfdbcublfoggqwz67neq

Improving Multi-agent Based Scheduling by Neurodynamic Programming [chapter]

Balázs Csanád Csáji, Botond Kádár, László Monostori
2003 Lecture Notes in Computer Science  
The paper outlines an attempt to enhance the performance of an agentbased manufacturing system by using adaptation and machine learning techniques.  ...  and material processing systems with adaptive, learning abilities on the other hand [11] .  ...  Every resource agent can learn how to direct ants passing it. To learn the promising scheduling traces we use temporal difference learning.  ... 
doi:10.1007/978-3-540-45185-3_11 fatcat:vlv5l4pi3rf7bndijzap2o26aq

Large-scale learning with AdaGrad on Spark

Asmelash Teka Hadgu, Aastha Nigam, Ernesto Diaz-Aviles
2015 2015 IEEE International Conference on Big Data (Big Data)  
In this work, we implement a distributed version of AdaGrad for large-scale machine learning tasks using Apache Spark.  ...  in machine learning today.  ...  In particular, AdaGrad alters the scheduling of the learning-rate to adapt based on historical information.  ... 
doi:10.1109/bigdata.2015.7364091 dblp:conf/bigdataconf/HadguND15 fatcat:dukkye4lkrakxdg7zzutku2xmq

FALCON: Fast and Accurate Multipath Scheduling using Offline and Online Learning [article]

Hongjia Wu, Ozgu Alay, Anna Brunstrom, Giuseppe Caso, Simone Ferlin
2022 arXiv   pre-print
FALCON builds on the idea of meta-learning where offline learning is used to create a set of meta-models that represent coarse-grained network conditions, and online learning is used to bootstrap a specific  ...  In this paper, we propose FALCON, a learning-based multipath scheduler that can adapt fast and accurately to time-varying network conditions.  ...  Existing multipath schedulers are either based on predefined rules (e.g., using the path with minimum Round Trip Time (RTT)) or on Machine Learning (ML) schemes (e.g., using a Reinforcement Learning (RL  ... 
arXiv:2201.08969v1 fatcat:lj2vlz5q45cbzabf4prs3pyp2q

Performance modeling of CMOS inverters using support vector machines (SVM) and adaptive sampling

Ashwin Satyanarayana
2016 Microprocessors and microsystems  
We use Support Vector Machines (SVMs) with Chernoff inequality to come up with an efficient adaptive sampling technique, for scaling down the data.  ...  Integrated circuit designs are verified through the use of circuit simulators before being reproduced in real silicon.  ...  (d) Convergence tests: The tests of convergence used in progressive sampling are not full proof, and the algorithm could converge at a local optimum (if the learning curve is not smooth) instead of the  ... 
doi:10.1016/j.micpro.2016.03.007 fatcat:gt3lwfzhr5h3jfnpswqtzh4vii

Towards End-to-End Quality of Service: Controlling I/O Interference in Shared Storage Servers [chapter]

Gokul Soundararajan, Cristiana Amza
2008 Lecture Notes in Computer Science  
Our experimental evaluation, using the MySQL database engine and OLTP benchmarks, shows the effectiveness of our technique in enforcing high-level application Service Level Objectives (SLOs) in shared  ...  Our approach uses coordinated learning based on the degree of achievement of high-level perapplication service level objectives.  ...  We show experimentally, using industry standard benchmarks, that our technique converges towards the optimal configuration and is effective in enforcing high-level application SLOs at the storage server  ... 
doi:10.1007/978-3-540-89856-6_15 fatcat:yfpyzc2drne37gotxrpqhw6e4m

Using of Machine Learning into Cloud Environment (A Survey): Managing and Scheduling of Resources in Cloud Systems

Elham Hormozi, Hadi Hormozi, Mohammad Kazem Akbari, Morteza Sargolzai Javan
2012 2012 Seventh International Conference on P2P, Parallel, Grid, Cloud and Internet Computing  
This technology holds a vast scope of using the various aspects of machine learning for increased performance and solving some of the challenges in front of the research community.  ...  In this survey, we investigate the effects using the concepts of machine learning on cloud environments, e.g. automated resource allocation mechanism, intelligently managing and allocating resources with  ...  Josep Ll. et al. in [13] , by using machine learning presented adaptive scheduling on power-aware managed data-centers.  ... 
doi:10.1109/3pgcic.2012.69 dblp:conf/3pgcic/HormoziHAJ12 fatcat:j5zh7osjybge7gng27wsbgzvn4

A State of Art Survey for Concurrent Computation and Clustering of Parallel Computing for Distributed Systems

Hanan Shukur, Subhi R. M. Zeebaree, Abdulraheem Jamil Ahmed, Rizgar R. Zebari, Omar Ahmed, Bareen Shams Aldeen Tahir, Mohammed A. M.Sadeeq
2020 Journal of Applied Science and Technology Trends  
The algorithms used in this system contain iterative and conditional control as a result of using them within advanced machine learning systems for instance using it in a recurrent neutral network (RNN  ...  .  TensorFlow has widely used in machine learning research and application in which several Google Services use this technique  The unified dataflow graph is used with the TensorFlow for representing  ... 
doi:10.38094/jastt1466 fatcat:g3gqvgn56rh3boyoqvrmbgd4iy

GCWOAS2: Multiobjective Task Scheduling Strategy Based on Gaussian Cloud-Whale Optimization in Cloud Computing

Lina Ni, Xiaoting Sun, Xincheng Li, Jinquan Zhang, Carmen De Maio
2021 Computational Intelligence and Neuroscience  
In the GCWOAS2 strategy, an opposition-based learning mechanism is first used to initialize the scheduling strategy to generate the optimal scheduling scheme.  ...  Then, an adaptive mobility factor is proposed to dynamically expand the search range.  ...  In addition, we also introduce an adaptive learning factor to make the search step in this strategy adaptive.  ... 
doi:10.1155/2021/5546758 fatcat:ls7ehk35ujgd7kdterl4ptrd2q
« Previous Showing results 1 — 15 out of 48,943 results