7 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 7 / 7
Yayın Calculating the VC-dimension of decision trees(IEEE, 2009) Aslan, Özlem; Yıldız, Olcay Taner; Alpaydın, Ahmet İbrahim EthemWe propose an exhaustive search algorithm that calculates the VC-dimension of univariate decision trees with binary features. The VC-dimension of the univariate decision tree with binary features depends on (i) the VC-dimension values of the left and right subtrees, (ii) the number of inputs, and (iii) the number of nodes in the tree. From a training set of example trees whose VC-dimensions are calculated by exhaustive search, we fit a general regressor to estimate the VC-dimension of any binary tree. These VC-dimension estimates are then used to get VC-generalization bounds for complexity control using SRM in decision trees, i.e., pruning. Our simulation results shows that SRM-pruning using the estimated VC-dimensions finds trees that are as accurate as those pruned using cross-validation.Yayın Budding trees(IEEE Computer Soc, 2014-08-24) İrsoy, Ozan; Yıldız, Olcay Taner; Alpaydın, Ahmet İbrahim EthemWe propose a new decision tree model, named the budding tree, where a node can be both a leaf and an internal decision node. Each bud node starts as a leaf node, can then grow children, but then later on, if necessary, its children can be pruned. This contrasts with traditional tree construction algorithms that only grows the tree during the training phase, and prunes it in a separate pruning phase. We use a soft tree architecture and show that the tree and its parameters can be trained using gradient-descent. Our experimental results on regression, binary classification, and multi-class classification data sets indicate that our newly proposed model has better performance than traditional trees in terms of accuracy while inducing trees of comparable size.Yayın On computing the multivariate poisson probability distribution(Springer, 2023-06-20) Çekyay, Bora; Frenk, Johannes Bartholomeus Gerardus; Javadi, SonyaWithin the theory of non-negative integer valued multivariate infinitely divisible distributions, the multivariate Poisson distribution plays a key role. As in the univariate case, any non-negative integer valued infinitely divisible multivariate distribution can be approximated by a multivariate distribution belonging to the compound Poisson family. The multivariate Poisson distribution is an important member of this family. In recent years, the multivariate Poisson distributions also has gained practical importance, since they serve as models to describe counting data having a positive covariance structure. However, due to the computational complexity of computing the multivariate Poisson probability mass function (pmf) and its corresponding cumulative distribution function (cdf), their use within these counting models is limited. Since most of the theoretical properties of the multivariate Poisson probability distribution seem already to be known, the main focus of this paper is on proposing more efficient algorithms to compute this pmf. Using a well known property of a Poisson multivariate distributed random vector, we propose in this paper a direct approach to calculate this pmf based on finding all solutions of a system of linear Diophantine equations. This new approach complements an already existing procedure depending on the use of recurrence relations existing for the pmf. We compare our new approach with this already existing approach applied to a slightly different set of recurrence relations which are easier to evaluate. A proof of this new set of recurrence relations is also given. As a result, several algorithms are proposed where some of them are based on the new approach and some use the recurrence relations. To test these algorithms, we provide an extensive analysis in the computational section. Based on the experiments in this section, we conclude that the approach finding all solutions of a set of linear Diophantine equations is computationally more efficient than the approach using the recurrence relations to evaluate the pmf of a multivariate Poisson distributed random vector.Yayın VC-dimension of univariate decision trees(IEEE-INST Electrical Electronics Engineers Inc, 2015-02-25) Yıldız, Olcay TanerIn this paper, we give and prove the lower bounds of the Vapnik-Chervonenkis (VC)-dimension of the univariate decision tree hypothesis class. The VC-dimension of the univariate decision tree depends on the VC-dimension values of its subtrees and the number of inputs. Via a search algorithm that calculates the VC-dimension of univariate decision trees exhaustively, we show that our VC-dimension bounds are tight for simple trees. To verify that the VC-dimension bounds are useful, we also use them to get VC-generalization bounds for complexity control using structural risk minimization in decision trees, i.e., pruning. Our simulation results show that structural risk minimization pruning using the VC-dimension bounds finds trees that are more accurate as those pruned using cross validation.Yayın A study on relationship between inventory level and sales quantity and an application from sportswear-retailing industry(Işık Üniversitesi, 2019-01-10) Bahçıvanoğlu, Can Ali; Ferman, Ali Murat; Işık Üniversitesi, Sosyal Bilimler Enstitüsü, Yöneticiler İçin İşletme Yönetimi Yüksek Lisans ProgramıIn my thesis i deeply analyze effect of invetory level of sales. I try to estimate 'how massive image' effects customers sale's decision.Yayın Predictive modelling of surface roughness and residual stress induced by milling of hot forged and heat treated AA7075(Springer Nature, 2025-11-03) Tok, Görkem; Dinçer, Ammar Tarık; Kuzu, Ali Taner; Bakkal, MustafaThis study investigates the influence of cutting parameters on residual stress and surface roughness during the milling of hot-forged and T6 heat-treated AA7075 components. Using Taguchi L9 and full-factorial experimental designs and regression modelling, the research highlights important relationships between cutting parameters (cutting speed, feed rate, and depth of cut), residual stress and surface roughness. Higher cutting speeds (350 m/min) and lower feed rates (0.1 mm/tooth) significantly minimized residual stresses, with hoop stress values decreasing from 108.7 MPa at lower speeds (150 m/min) to approximately 73.4 MPa at higher speeds, and axial stress values ranging from 45.9 MPa to 88.5 MPa. Surface roughness (Ra) was most influenced by feed rate, with measurement values varying between 0.25 mu m and 0.92 mu m. Support Vector Regression (SVR) demonstrated better accuracy for predicting residual stress (MAPE: 11.5%) and surface roughness (MAPE: 7%), outperforming Lasso and Ridge regression models. These findings provide a consistent framework for optimizing cutting parameters and enhancing residual stress and surface roughness in AA7075 machining processes, offering practical implications for improving component performance and manufacturing efficiency.Yayın Investigation and prediction of surface integrity induced by milling of hot forged and heat treated AA7075(Motto, 2024-11-03) Tok, Görkem; Dinçer, Ammar Tarık; Kuzu, Ali Taner; Bakkal, Mustafa; Saklakoğlu, İ. EtemThis study examines the influence of cutting parameters on surface integrity, focusing on residual stress and surface roughness, in hot-forged and T6 heat-treated AA7075 components post-milling. Using the Taguchi L9 DOE method, orthogonal cutting milling experiments were performed, with residual stress measured via nondestructive X-ray diffraction (XRD). The analysis indicated that lower cutting speeds reduce residual stress, with down milling causing compressive and up milling causing tensile stresses. A proposed model showed a significant correlation between cutting force and residual stress—higher cutting forces increased residual stress. Surface roughness assessment revealed that feed rate greatly impacts residual stress, with lower feed rates reducing roughness. These insights will aid in developing a regression model for predicting outcomes in future experiments, enhancing the understanding and control of surface integrity in milling AA7075 components.
