Results 271 to 280 of about 33,603 (293)
Some of the next articles are maybe not open access.
Model Optimisation Techniques for Convolutional Neural Networks
2022Deep neural networks provide good results for computer vision tasks. This has been possible due to a renewed interest in neural networks, availability of large-scale labelled training data, virtually unlimited processing and storage on cloud platforms and high-performance clusters.
Nazir, Sajid +2 more
openaire +2 more sources
An Optimised Optional Randomised Response Technique
International Statistical ReviewSummaryIn this paper, we begin by reviewing the optional randomised response technique estimator (ORRTE) developed by Chaudhuri and Mukerjee for estimating the proportion of a sensitive characteristic in a population. We show that their estimator is unbiased and has smaller variance than the Warner's estimator.
Kavya Pushadapu +2 more
openaire +2 more sources
Optimisation techniques for roof layout
Proceedings of IEEE Region 10 International Conference on Electrical and Electronic Technology. TENCON 2001 (Cat. No.01CH37239), 2002The roof sheet layout problem is a constrained version of the general cutting problem (Cranny, Bossomaier & Sibley-Punnett, 1999). Raidl (eds. Fogel, Angeline & Back, 1996) aptly describes the general cutting problem, and offers a possible solution using a skilful genotype decoding mechanism. A version of this technique Is used in this research.
L. Sibley-Punn, T. Bossomaier
openaire +1 more source
Comparisons of Optimisation Techniques
2002In this chapter, theoretical studies which variously prove global convergence, or compare rates of convergence, are listed and contrasted for a range of optimisation methods. These results then lead to a consideration of empirical studies, on test functions, combinatorial optimisation problems, and systems models.
openaire +1 more source
Constraint resolution using optimisation techniques
Computers & Graphics, 2001Abstract Constraint-based CAD systems are useful for handling design applications in which the precise rules are not known beforehand. The designer can introduce new constraints as these become apparent as the design task proceeds. A variety of ways for resolving constraints currently exist.
openaire +1 more source
Optimising quarrying techniques and practices
2004The European Regions, today rather poor in metalliferous and energetic commodities which could be economically exploited, are, on the contrary, naturally rich in natural stone resources. Ever since stone has represented in Europe a very important resource and, indeed, it is a part of our historic-artistic heritage, as its use as a construction material
CARDU, Marilena, LOVERA E.
+6 more sources
The Information Limit Optimisation Technique
1993It is important not to over, or under, parameterise a data set during analysis, as otherwise physically unreliable values will result. This problem is of considerable concern in the analysis of eclipsing binary light curves, where it is always tempting to include the effects of more “accurate” formulations, or of additional, physical processes.
openaire +1 more source
Optimisation of network structure using genetic techniques
1990 IJCNN International Joint Conference on Neural Networks, 1990Arguments contending that it is necessary to use structured neural networks for the solution of certain problem types are presented. Structure is imposed on connectivity, activation functions, and other parameters of the network to simultaneously optimize generalization ability and compactness of the network.
openaire +1 more source
Enhancing motion cueing using an optimisation technique
The Aeronautical Journal, 2018ABSTRACTVirtual engineering tools are not currently employed extensively during the certification and commissioning of flight simulator motion systems. Subjective opinion is regarded as sufficient for most applications, as it provides verification that the motion platform does not cause false cueing.
openaire +2 more sources