Filters








82,262 Hits in 6.1 sec

Moving away from error-based learning in multi-objective estimation of distribution algorithms

Luis Martí, Jesús García, Antonio Berlanga, José M. Molina
2010 Proceedings of the 12th annual conference on Genetic and evolutionary computation - GECCO '10  
In this work we analyze the model-building issue and the requirements it imposes on the learning paradigm being used.  ...  as described for the HypE algorithm.  ...  INTRODUCTION Multi-objective optimization has received lot of attention by the evolutionary computation community leading to multi-objective evolutionary algorithms (MOEAs) (cf. [2] ).  ... 
doi:10.1145/1830483.1830585 dblp:conf/gecco/MartiGBM10 fatcat:n2a4ntmwofcihpc6v7553ocbzu

Neural network approach to ECT inverse problem solving for estimation of gravitational solids flow

Hela Garbaa, Lidia Jackowska-Strumiłło, Krzysztof Grudzień, Andrzej Romanowski
2014 Proceedings of the 2014 Federated Conference on Computer Science and Information Systems  
Our method is based on artificial neural network to estimate the radius of an object present inside a pipeline. This information is useful to predict the distribution of material inside the pipe.  ...  The capacitance data used to train and test the neural network is simulated on Matlab using the electrical capacitance tomography toolkit ECTsim.  ...  A Multi-Layer Perceptron with a single hidden layer is applied to estimate the radius of the object inside the pipe.  ... 
doi:10.15439/2014f368 dblp:conf/fedcsis/GarbaaJGR14 fatcat:hzd6dwjhlngqbg3dg6r46nlole

Multi-class probabilistic classification using inductive and cross Venn–Abers predictors

Valery Manokhin
2022 Zenodo  
We present a new approach to multi-class probability estimation by turning IVAPs and CVAPs into multi- class probabilistic predictors.  ...  The proposed multi-class predictors are experimentally more accurate than both uncalibrated predictors and existing calibration methods.  ...  Vladimir Vovk for his suggestion on the subject of my research and his generous and continuing help and support during my studies at Royal Holloway, University of London.  ... 
doi:10.5281/zenodo.6467179 fatcat:h7inssumfraf5laz42622jbumu

Advancing Model–Building for Many–Objective Optimization Estimation of Distribution Algorithms [chapter]

Luis Martí, Jesús García, Antonio Berlanga, José M. Molina
2010 Lecture Notes in Computer Science  
In this work we dissect this issue and propose a set of algorithms that can be used to bridge the gap of MOEDA application. A set of experiments are carried out in order to sustain our assertions.  ...  In order to achieve a substantial improvement of MOEDAs regarding MOEAs it is necessary to adapt their model-building algorithms.  ...  Estimation of Distribution Algorithms Estimation of distribution algorithms (EDAs) have been claimed as a paradigm shift in the field of evolutionary computation.  ... 
doi:10.1007/978-3-642-12239-2_53 fatcat:it6ii6q5c5e6his6cloaqfhbii

Synergies between Evolutionary Algorithms and Reinforcement Learning

Madalina M. Drugan
2015 Proceedings of the Companion Publication of the 2015 on Genetic and Evolutionary Computation Conference - GECCO Companion '15  
setups Evolutionary multi-objective optimisation (EMO) in RL •Multi-objective Markov Decision Processes (MOMDPs) • compute all Pareto optimal policies • tuples of rewards instead of a single reward •  ...  • Pursuit with probability the operator v with the maximal estimated reward • Get reward vector for the operator v • Update reward value using the immediate reward • High rank the estimated reward distribution  ...  heuristics should be independent of the type of heuristic it is applied on 63 Concluding remarks on reinforcement learning for evolutionary computation • Most EC algorithms use model free RL or multi-armed  ... 
doi:10.1145/2739482.2756582 dblp:conf/gecco/Drugan15 fatcat:5jedfs4jmfgclcpppzcjvz6yvu

Keywords

2020 2020 17th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)  
a New Appearance Model for Multiple-Object-Tracking Multi-robot Multi-robot manipulation using formation control and human-in-the-loop scheme Myo Comparison of EMG signal classification algorithms  ...  A Clustering Method Based on the Artificial Bee Colony Algorithm for Gas Sensing Gauss-newton Performance Comparison of Positioning Algorithms for UAV Navigation Purposes based on Estimated Distances  ... 
doi:10.1109/cce50788.2020.9299167 fatcat:xu346wrfmzhsbbxumvxd2g3zzm

Editorial: Engineering Applications of Neurocomputing

Long Wang, Zhe Song, Zijun Zhang, Chao Huang
2022 Frontiers in Neurorobotics  
AUTHOR CONTRIBUTIONS LW wrote the manuscript. ZZ, ZS, and CH edited the manuscript. All authors contributed to the article and approved the submitted version.  ...  vision system based on a deep neural network with RGB-D image inputs for object recognition and 6D pose estimation.  ...  The 2D pixels and 3D points in cropped object regions were then fed into a pose estimation network to make object pose predictions based on the fusion of color and geometry features.  ... 
doi:10.3389/fnbot.2022.839505 pmid:35153710 pmcid:PMC8832117 fatcat:sqle6aq27jcvjctfudzu24owfu

Method-Induced Errors in Fractal Analysis of Lung Microscopic Images Segmented with the Use of HistAENN (Histogram-Based Autoencoder Neural Network)

Dorota Oszutowska-Mazurek, Przemyslaw Mazurek, Miroslaw Parafiniuk, Agnieszka Stachowicz
2018 Applied Sciences  
The designing of Computer-Aided Diagnosis (CADx) is necessary to improve patient condition analysis and reduce human error.  ...  HistAENN (Histogram-based Autoencoder Neural Network, the first hierarchy level) and the fractal-based estimator (the second hierarchy level) are assumed for segmentation and image analysis, respectively  ...  We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X GPU used for this research. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app8122356 fatcat:vwxvmrdzcrghbf6xhbzclipg2m

Augmenting depth estimation from deep convolutional neural network using multi-spectral photometric stereo

Yisong Luo, Hengchao Jiao, Lin Qi, Junyu Dong, Shu Zhang, Hui Yu
2017 2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI)  
on each of the RGB channels.  ...  Experiments demonstrate the competitive results of our method for improving the depth estimation. Index Terms-deep estimation, convolutional neural network, multi-spectral photometric stereo  ...  The scheme consists of two main parts: (a) a deep convolutional neural network and (b) a multi-spectral PS algorithm.  ... 
doi:10.1109/uic-atc.2017.8397464 dblp:conf/uic/LuoJQDZY17 fatcat:zlgr55yjnng27bihec3oqqlfwe

DiNNO: Distributed Neural Network Optimization for Multi-Robot Collaborative Learning [article]

Javier Yu, Joseph A. Vincent, Mac Schwager
2021 arXiv   pre-print
We present a distributed algorithm that enables a group of robots to collaboratively optimize the parameters of a deep neural network model while communicating over a mesh network.  ...  We compare our algorithm to two existing distributed deep neural network training algorithms in (i) an MNIST image classification task, (ii) a multi-robot implicit mapping task, and (iii) a multi-robot  ...  The authors of [22] propose using local convex approximations, based on global gradient estimates found through gradient tracking, for distributed neural network optimization and show basic results on  ... 
arXiv:2109.08665v1 fatcat:tfmyej6rmbgmzpv2fpkcfvg73i

A Perspective of Conventional and Bio-inspired Optimization Techniques in Maximum Likelihood Parameter Estimation

Yongzhong Lu, Min Zhou, Shiping Chen, David Levy, Jicheng You
2018 Journal of Autonomous Intelligence  
Maximum likelihood estimation is a method of estimating the parameters of a statistical model in statistics.  ...  Over the past decade, although many conventional numerical approximation approaches have been most successfully developed to solve the problems of maximum likelihood parameter estimation, bio-inspired  ...  The authors also gratefully acknowledge the helpful comments and suggestions of the reviewers, which have improved the presentation.  ... 
doi:10.32629/jai.v1i2.28 fatcat:7hfsl4shkjbpvggyvydwgv2lle

Optimization Techniques for History Matching and Production Forecasting

2019 International journal of recent technology and engineering  
Since the reservoirs are highly heterogeneous and nonlinear in nature, it is often difficult to obtain accurate estimates of the spatial distribution of reservoir properties representing the reservoir  ...  If an accurate model of a reservoir is built, it can lead to efficient management of the reservoir.  ...  Saraf, former Distinguished Professor, UPES, Dehradun, for their continuous guidance and support throughout the study.  ... 
doi:10.35940/ijrte.c6287.118419 fatcat:evv3s2wbkjgsjh6mehszg76obu

A Multi-level procedure for enhancing accuracy of machine learning algorithms [article]

Kjetil O. Lye, Siddhartha Mishra, Roberto Molinaro
2020 arXiv   pre-print
We propose a multi-level method to increase the accuracy of machine learning algorithms for approximating observables in scientific computing, particularly those that arise in systems modeled by differential  ...  Moreover, we also apply the multi-level algorithm in the context of forward uncertainty quantification and observe a considerable speed-up over competing algorithms.  ...  The research of SM was partially supported by European Research Council Consolidator grant ERCCoG 770880: COMANFLO.  ... 
arXiv:1909.09448v2 fatcat:bc3fjgslhzdclddbeey3hn6asy

Applications of Soft Computing in Civil Engineering: A Review

Vinay Chandwani, Vinay Agrawal, Ravindra Nagar
2013 International Journal of Computer Applications  
The review paper presents the applications of two major Soft Computing techniques viz., Artificial Neural Networks and Genetic Algorithms in the field of Civil Engineering, which to some extent has replaced  ...  Soft Computing being a multi-disciplinary field uses a variety of statistical, probabilistic and optimization tools which complement each other to produce its three main branches viz., Neural Networks,  ...  Fu and Kapelan [92] investigated the use of ANN in combination with GA to improve the computational efficiency in solving the multi-objective water distribution system design problems.  ... 
doi:10.5120/14047-2210 fatcat:ed46xbfhufbdjpdaal6zk4ozoe

Enhanced Performance of Multi Class Classification of Anonymous Noisy Images

Ajay Kumar Singh, V P Shukla, Sangappa R. Biradar, Shamik Tiwari
2014 International Journal of Image Graphics and Signal Processing  
The zeromean property of the distribution allows such noise to be removed by locally averaging pixel values [19] .  ...  Columbia Object Image Library (COIL-100) is a database of colour images of 100 objects. The objects were placed on a motorized turntable against a black background.  ... 
doi:10.5815/ijigsp.2014.03.04 fatcat:fuhbnr4gtjgkhh4e5w4igsalbe
« Previous Showing results 1 — 15 out of 82,262 results