Detail of "6576-51-8"

Reference

Stallimycin hydrochloride

Stallimycin hydrochloride. De Angelis, L. (Spain). Med. Actual., 13(8), 319-26 (English/Spanish) 1977. CODEN: MDACAP. DOCUMENT TYPE: Journal; General Review CA Section: 63 (Pharmaceuticals) A review with 27 refs. of stallimycin-HCl (I) [6576-51-8] phys. properties, action and uses, toxicity, side effects, etc.

Hybridized particle swarm algorithm for adaptive structure training of multilayer feed-forward neural network: QSAR studies of bioactivity of organic compounds

Hybridized particle swarm algorithm for adaptive structure training of multilayer feed-forward neural network: QSAR studies of bioactivity of organic compounds. Shen, Qi; Jiang, Jian-Hui; Jiao, Chen-Xu; Lin, Wei-Qi; Shen, Guo-Li; Yu, Ru-Qin (State Key Laboratory of Chemo/Biosensing and Chemometrics, College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, Peop. Rep. China). Journal of Computational Chemistry, 25(14), 1726-1735 (English) 2004 John Wiley & Sons, Inc. CODEN: JCCHDD. ISSN: 0192-8651. DOCUMENT TYPE: Journal CA Section: 1 (Pharmacology) The multilayer feed-forward ANN is an important modeling technique used in QSAR studying. The training of ANN is usually carried out only to optimize the wts. of the neural network and without paying attention to the network topol. Some other strategies used to train ANN are, first, to discover an optimum structure of the network, and then to find wts. for an already defined structure. These methods tend to converge to local optima, and may also lead to overfitting.In this study，6576-51-8 is also used. In this article, a hybridized particle swarm optimization (PSO) approach was applied to the neural network structure training (HPSONN). The continuous version of PSO was used for the wt. training of ANN, and the modified discrete PSO was applied to find appropriate the network architecture. The network structure and connectivity are trained simultaneously. The two versions of PSO can jointly search the global optimal ANN architecture and wts. A new objective function is formulated to det. the appropriate network architecture and optimum value of the wts. The proposed HPSONN algorithm was used to predict carcinogenic potency of arom. amines and biol. activity of a series of distamycin and distamycin-like derivs. The results were compared to those obtained by PSO and GA training in which the network architecture was kept fixed. The comparison demonstrated that the HPSONN is a useful tool for training ANN, which converges quickly towards the optimal position, and can avoid overfitting in some extent. .