The aim of this paper, is to discuss several high performance training algorithms fall into two main categories. The first category uses heuristic techniques, which were developed from an analysis of the performance of the standard gradient descent algorithm. The second category of fast algorithms uses standard numerical optimization techniques such as: quasi-Newton . Other aim is to solve the drawbacks related with these training algorithms and propose an efficient training algorithm for FFNN

In many video and image processing applications, the frames are partitioned into blocks, which are extracted and processed sequentially. In this paper, we propose a fast algorithm for calculation of features of overlapping image blocks. We assume the features are projections of the block on separable 2D basis functions (usually orthogonal polynomials) where we benefit from the symmetry with respect to spatial variables. The main idea is based on a construction of auxiliary matrices that virtually extends the original image and makes it possible to avoid a time-consuming computation in loops. These matrices can be pre-calculated, stored and used repeatedly since they are independent of the image itself. We validated experimentally th

Big data analysis has important applications in many areas such as sensor networks and connected healthcare. High volume and velocity of big data bring many challenges to data analysis. One possible solution is to summarize the data and provides a manageable data structure to hold a scalable summarization of data for efficient and effective analysis. This research extends our previous work on developing an effective technique to create, organize, access, and maintain summarization of big data and develops algorithms for Bayes classification and entropy discretization of large data sets using the multi-resolution data summarization structure. Bayes classification and data discretization play essential roles in many learning algorithms such a

Two unsupervised classifiers for optimum multithreshold are presented; fast Otsu and k-means. The unparametric methods produce an efficient procedure to separate the regions (classes) by select optimum levels, either on the gray levels of image histogram (as Otsu classifier), or on the gray levels of image intensities(as k-mean classifier), which are represent threshold values of the classes. In order to compare between the experimental results of these classifiers, the computation time is recorded and the needed iterations for k-means classifier to converge with optimum classes centers. The variation in the recorded computation time for k-means classifier is discussed.

Traffic classification is referred to as the task of categorizing traffic flows into application-aware classes such as chats, streaming, VoIP, etc. Most systems of network traffic identification are based on features. These features may be static signatures, port numbers, statistical characteristics, and so on. Current methods of data flow classification are effective, they still lack new inventive approaches to meet the needs of vital points such as real-time traffic classification, low power consumption, ), Central Processing Unit (CPU) utilization, etc. Our novel Fast Deep Packet Header Inspection (FDPHI) traffic classification proposal employs 1 Dimension Convolution Neural Network (1D-CNN) to automatically learn more representational c