Learn More
Generalized linear models with nonlinear feature transformations are widely used for large-scale regression and classification problems with sparse inputs. Memorization of feature interactions through a wide set of cross-product feature transformations are effective and interpretable, while generalization requires more feature engineering effort. With less(More)
The reactions of hexachlorocyclotriphosphazatriene, N(3)P(3)Cl(6), with mono- (1 and 2) and bisferrocenyldiamines (3-5), FcCH(2)NH(CH(2))(n)NHR(1) (R(1) = H or FcCH(2)-), produce mono- (6 and 7) and spirocyclic bisferrocenylphosphazenes (8-10). The fully substituted phosphazenes (11-15 and 18-21) are obtained from the reactions of corresponding partly(More)
The feature selection approach provides improved prediction and minimizes the computation time. Due to the higher numbers of features the understanding of the data in pattern recognition becomes difficult sometimes. That's why researchers have used different feature selection techniques with the single classifiers in their intrusion detection system to(More)
A number of novel ansa-spiro-ansa (asa) cyclotetraphosphazenes (1a-5b) was prepared in the range of 63-90 % yields. The structures of the compounds were verified by MS, FTIR, (1)H, (13)C{(1)H} and (31)P{(1)H} NMR, heteronuclear single quantum coherence (HSQC), and heteronuclear multiple-bond correlation (HMBC) techniques. The crystal structures of 1b, 2c(More)
Artificial intelligence techniques of neural network and fuzzy systems were applied as alternative methods to determine beach litter grading, based on litter surveys of the Antalya coastline (the Turkish Riviera). Litter measurements were categorized and assessed by artificial intelligence techniques, which lead to a new litter categorization system. The(More)
A number of partly (7-9) and fully (10a-12d, Scheme 1) substituted mono(4-fluorobenzyl)spiro cyclotriphosphazenes was prepared. The structures of the compounds were determined by MS, FTIR, 1D and 2D NMR techniques. The crystal structures of 9, 11b and 12b were verified by X-ray diffraction analysis. In vitro cytotoxic activity of the phosphazenes (10a-12d)(More)
Utilization of the data mining techniques in intrusion detection systems is common for the classification of the network events as either normal events or attack events. Naïve Bayes (NB) method is a simple, efficient and popular data mining method that is built on conditional independence of attributes assumption. Hidden Naïve Bayes (HNB) is(More)
Overview We've organized our presentation into three stages: 1. A more detailed coverage of the building blocks of CNNs 2. Attempts to explain how and why Residual Networks work 3. Survey extensions to ResNets and other notable architectures Topics covered: ● Alternative activation functions ● Relationship between fully connected layers and convolutional(More)