502 Hits in 6.0 sec

Augmented neural networks and problem structure-based heuristics for the bin-packing problem

Nihat Kasap, Anurag Agarwal
2012 International Journal of Systems Science  
In this article, we report on a research project where we applied augmented-neural-networks (AugNNs) approach for solving the classical bin-packing problem (BPP).  ...  We discuss the characteristics of problems on which such problem structure-based heuristics could be applied.  ...  In this article, we apply a neural network-based approach called augmented neural networks (AugNNs) for the BPP, and also a decomposition approach involving heuristics that exploit the problem structure  ... 
doi:10.1080/00207721.2010.549587 fatcat:afybvh7tfveojlzty7pfefolna

A Multi-task Selected Learning Approach for Solving 3D Flexible Bin Packing Problem [article]

Lu Duan, Haoyuan Hu, Yu Qian, Yu Gong, Xiaodong Zhang, Yinghui Xu, Jiangwen Wei
2019 arXiv   pre-print
The existing heuristic methods for classic 3D bin packing don't work well for this particular NP-hard problem and designing a good problem-specific heuristic is non-trivial.  ...  A 3D flexible bin packing problem (3D-FBPP) arises from the process of warehouse packing in e-commerce.  ...  Base on Pointer Network, [2] develops a neural combinatorial optimization framework with RL, which solves some classical problems, such as TSP and Knapsack Problem.  ... 
arXiv:1804.06896v3 fatcat:ldg7aohvwnhnzbjxcshxkst4u4

A Generalized Reinforcement Learning Algorithm for Online 3D Bin-Packing [article]

Richa Verma, Aniruddha Singhal, Harshad Khadilkar, Ansuma Basumatary, Siddharth Nayak, Harsh Vardhan Singh, Swagat Kumar, Rajesh Sinha
2020 arXiv   pre-print
We propose a Deep Reinforcement Learning (Deep RL) algorithm for solving the online 3D bin packing problem for an arbitrary number of bins and any bin size.  ...  Simulation results show that the RL-based method outperforms state-of-the-art online bin packing heuristics in terms of empirical competitive ratio and volume efficiency.  ...  Similarly, (Mao et al. 2017 ) has used neural networks to select the heuristic based on feature information collected from the items and the bins.  ... 
arXiv:2007.00463v1 fatcat:fnvpgbpfifappodedsuatlgqum

Contrasting meta-learning and hyper-heuristic research: the role of evolutionary algorithms

Gisele L. Pappa, Gabriela Ochoa, Matthew R. Hyde, Alex A. Freitas, John Woodward, Jerry Swan
2013 Genetic Programming and Evolvable Machines  
This discussion focuses on the dimensions of the problem space, the algorithm space and the performance measure, as well as clarifying important issues related to different levels of automation and generality  ...  (classification) and hyper-heuristics in the field of optimisation.  ...  Hyper-heuristics for 2D packing: selecting versus generating components This section presents two hyper-heuristics for the 2D strip packing problem, one based on the selection approach and the other in  ... 
doi:10.1007/s10710-013-9186-9 fatcat:rxkljeappbea5m6bjmwahuqf24

Function of Artificial Intelligence in Production Scheduling: A Critical Evaluation and Comparison of Key Approaches

Brahma Datta Shukla
2018 International Journal for Research in Applied Science and Engineering Technology  
This extensive area covers diverse variety of problems as; vehicle routing problem, bin packing problem and job priority.  ...  Several of these metaheuristic methods are guiding the literature of production scheduling for past two decade, as; Genetic Algorithm, Neural Network, and Fuzzy Logic which will be discuss in this paper  ...  This neural network is extensive to a three dimensional structure called neuro box network (NBN) where the three axes correspond to time, machine and part.  ... 
doi:10.22214/ijraset.2018.1412 fatcat:omssaspwnvbi5cgq43oicqaani

Backward Chaining [chapter]

2013 Encyclopedia of Operations Research and Management Science  
the use of artificial neural networks for evaluating loan applications, and the use of facility location theory for opening new branches and placing automatic teller machines (e.g., Harker and Zenios 1999  ...  One major strand of research is devoted to the development of stochastic models for the term structure of interest rates.  ...  The basic approach is also used to obtain level-oriented heuristics for solving two-dimensional bin packing problems.  ... 
doi:10.1007/978-1-4419-1153-7_200968 fatcat:wsdsqf2wxrckvpoq4yh5f7rsqm

Learning Practically Feasible Policies for Online 3D Bin Packing [article]

Hang Zhao, Chenyang Zhu, Xin Xu, Hui Huang, Kai Xu
2021 arXiv   pre-print
We tackle the Online 3D Bin Packing Problem, a challenging yet practically useful variant of the classical Bin Packing Problem.  ...  Agent must directly pack these items into the target bin stably without changing their arrival order, and no further adjustment is permitted.  ...  The most typical bin packing problem is 1D-BPP which seeks for an assignment of a collection of items with various scalar weights to multiple bins and minimizes the used bin number.  ... 
arXiv:2108.13680v2 fatcat:futvzrptc5f7zbeajoph64yzxy

Information Bottleneck Theory Based Exploration of Cascade Learning

Xin Du, Katayoun Farrahi, Mahesan Niranjan
2021 Entropy  
We evaluate this effect by proposing an information transition ratio, I(T;Y)/I(X;T), and show that it can serve as a useful heuristic in setting the depth of a neural network that achieves satisfactory  ...  In solving challenging pattern recognition problems, deep neural networks have shown excellent performance by forming powerful mappings between inputs and targets, learning representations (features) and  ...  Acknowledgments: We thank the anonymous reviewers for their constructive comments. 2021, 23, 1360  ... 
doi:10.3390/e23101360 pmid:34682084 pmcid:PMC8535168 fatcat:hw3fatomx5hdzmhvygsc263hyu

An Order Based Memetic Evolutionary Algorithm for Set Partitioning Problems [chapter]

Christine L. Mumford
2008 Studies in Computational Intelligence  
Note however, that heuristics based on vertex/item degrees have no meaning in this context, so the increasing and decreasing total degree heuristics are not appropriate for bin packing.  ...  In addition, there are many examples of hybrid (or memetic) approaches where problem specific heuristics, or other techniques such as neural networks or simulated annealing, have been incorporated into  ... 
doi:10.1007/978-3-540-78293-3_21 fatcat:xyo7lank5vavxl4vsl37bz6doy

Metaheuristic Approaches for One-Dimensional Bin Packing Problem: A Comparative Performance Study

Chanalea Munien, Shiv Mahabeer, Esther Dzitiro, Sharad Singh, Siluleko Zungu, Absalom E. Ezugwu
2020 IEEE Access  
In this paper, the one-dimensional bin packing problem is solved through the implementation of two underlying heuristics, namely, best fit and better fit, and four representative state-of-the-art global  ...  Nevertheless, this heuristic can produce near-optimal solutions and a good packing schema for most instances.  ...  The authors evaluated their presented strategy by applying the improved algorithm for training feedforward neural networks for two benchmark classification problems, an iris dataset and a breast cancer  ... 
doi:10.1109/access.2020.3046185 fatcat:rnvf7r34ibepzd3noqkejxpsf4

Industrial Robot Grasping with Deep Learning using a Programmable Logic Controller (PLC) [article]

Eugen Solowjow, Ines Ugalde, Yash Shahapurkar, Juan Aparicio, Jeff Mahler, Vishal Satish, Ken Goldberg, Heiko Claussen
2020 arXiv   pre-print
Two neural networks are deployed on a novel industrial AI hardware acceleration module close to a PLC with a power footprint of less than 10 W for the overall system.  ...  The software is tightly integrated with the hardware allowing for fast and efficient data processing and real-time communication.  ...  for neural network inputs.  ... 
arXiv:2004.10251v1 fatcat:kp6z473tdvcsvaggepfa3k2nc4

A Survey on the Current Challenges of Energy-Efficient Cloud Resources Management

Ikhlasse Hamzaoui, Benjamin Duthil, Vincent Courboulay, Hicham Medromi
2020 SN Computer Science  
In this same perspective, we survey some recent efforts made in energy-efficient virtual and containerized resources, by emphasizing first the most used reactive then proactive techniques for managing  ...  Efficient use of cloud's resources becomes then the driven force ensuring both, the satisfaction of service-level agreements and the sobriety of cloud's energy consumption.  ...  The first one is a multidimensional vector bin packing that uses a heuristic based on the WDP (weight dot product) to allocate PMs to VMs.  ... 
doi:10.1007/s42979-020-0078-9 fatcat:iefbzidmtzdarne2wmy54ctw3a

Neural Networks for Combinatorial Optimization: A Review of More Than a Decade of Research

Kate A. Smith
1999 INFORMS journal on computing  
This article briefly summarizes the work that has been done and presents the current standing of neural networks for combinatorial optimization by considering each of the major classes of combinatorial  ...  It has been over a decade since neural networks were first applied to solve combinatorial optimization problems.  ...  Acknowledgements The author is grateful to three anonymous referees, an associate editor, Dr. M. Gendreau, and Dr. B. Golden for their helpful comments and suggestions.  ... 
doi:10.1287/ijoc.11.1.15 fatcat:jy5jur2pyjhndpi45argti2f54


2015 Procedia Computer Science  
Hyper-heuristic for Permutation Flowshop Scheduling Problem H.  ...  on Tabu Search and Memetic Algorithm for Augmented Reality T.  ... 
doi:10.1016/s1877-0509(15)02460-6 fatcat:45i4mfbakrh6zdlmlifszpy32m

Optimization of Surface Utilization Using Heuristic Approaches

Yves Langer, Maud Bay, Yves Crama, Frédéric Bair, Jean-David Caprace, Philippe Rigo
2005 Ship Technology Research  
The solution combines a Guided Local Search heuristic with Fast Local Search techniques.  ...  A final discussion explains the additional real-life issues arising in the industrial application and how firm-specific constraints can be conveniently considered by the model.  ...  Acknowledgments We thank Chantiers de l'Atlantique (ALSTOM, Saint-Nazaire, France) for their support in this work and the problem definition.  ... 
doi:10.1179/str.2005.52.3.007 fatcat:qes5o2nfivaypkesjw7gjsogkq
« Previous Showing results 1 — 15 out of 502 results