In this paper we describe several different training algorithms for feed forward neural networks(FFNN). In all of these algorithms we use the gradient of the performance function, energy function, to determine how to adjust the weights such that the performance function is minimized, where the back propagation algorithm has been used to increase the speed of training. The above algorithms have a variety of different computation and thus different type of form of search direction and storage requirements, however non of the above algorithms has a global properties which suited to all problems.

This research includes synthesis of new heterocyclic derivatives of N-benzyl-5-bromoisatin. New 1, 2, 4-triazole, oxazoline and thiazoline derivatives of [N-benzyl-5-bromo-3-(Ethyliminoacetate)-indole-2-one] (2) have been synthesized. The preparation process started by the reaction of 5-bromoisatin with sodium hydride in dimethylformamide (DMF) at 0°C, gave suspension of sodium salt of 5-bromoisatin and subsequent reaction with benzylchloride to give N-benzyl-5-bromoisatin (1). Compound (1) reacted with ethylglycinate (Schiff base) obtained the intermediate compound (2) which reacted with different reagents in two ways. The first way, compound (2) reacted with (hydrazine hydrate, semicarbazide, phenylsemicarbazide and thiosemicarbazide)

A new series of Schiff bases compounds , containing an azomethine linkage was synthesized and expected to be biologically active .The structures of these compounds were identified by IR , Uv/vis spectra , melting points and followed by T.L.C.The biological activity of these compounds was studied

The reaction of starting materials (L-asCl2):bis[O,O-2,3;O,O-5,6-(chloro(carboxylic) methylidene)]- -L-ascorbic acid] with glycine gives new product bis[O,O-2,3,O,O-5,6-(N,O-di carboxylic methylidene N-glycine)-L-ascorbic acid] (L-as-gly) which is isolated and characterized by, Mass spectrum UV-visible and Fourier transform infrared spectrophotometer (FT-IR) . The reaction of the (L-as-gly) with M+2; Co(II) Ni(II) Cu(II) and Zn(II) has been characterized by FT- IR , Uv-Visible , electrical conductivity, magnetic susceptibility methods and atomic absorption and molar ratio . The analysis showed that the ligand coordinate with metal ions through mono dentate carboxylic resulting in six-coordinated with Co(II) Ni(II) Cu(II) ions while with

The continuous advancement in the use of the IoT has greatly transformed industries, though at the same time it has made the IoT network vulnerable to highly advanced cybercrimes. There are several limitations with traditional security measures for IoT; the protection of distributed and adaptive IoT systems requires new approaches. This research presents novel threat intelligence for IoT networks based on deep learning, which maintains compliance with IEEE standards. Interweaving artificial intelligence with standardization frameworks is the goal of the study and, thus, improves the identification, protection, and reduction of cyber threats impacting IoT environments. The study is systematic and begins by examining IoT-specific thre

Huge number of medical images are generated and needs for more storage capacity and bandwidth for transferring over the networks. Hybrid DWT-DCT compression algorithm is applied to compress the medical images by exploiting the features of both techniques. Discrete Wavelet Transform (DWT) coding is applied to image YCbCr color model which decompose image bands into four subbands (LL, HL, LH and HH). The LL subband is transformed into low and high frequency components using Discrete Cosine Transform (DCT) to be quantize by scalar quantization that was applied on all image bands, the quantization parameters where reduced by half for the luminance band while it is the same for the chrominance bands to preserve the image quality, the zig

Identifying breast cancer utilizing artificial intelligence technologies is valuable and has a great influence on the early detection of diseases. It also can save humanity by giving them a better chance to be treated in the earlier stages of cancer. During the last decade, deep neural networks (DNN) and machine learning (ML) systems have been widely used by almost every segment in medical centers due to their accurate identification and recognition of diseases, especially when trained using many datasets/samples. in this paper, a proposed two hidden layers DNN with a reduction in the number of additions and multiplications in each neuron. The number of bits and binary points of inputs and weights can be changed using the mask configuration