Search

This paper proposes a Neurocomputing application that reorders the Web results obtained from different Web Search Engines emulating the way our brain takes decisions. The proposed application is based on the Random Neural Network with Deep Learning Clusters that evaluates and adapts Web result relevance by associating independently each Deep Learning Cluster to a specific Web Search Engine. In addition, this paper presents a Deep Learning Cluster to perform as a Management Cluster that decides the final result relevance based on the inputs from each independent Deep Learning cluster. The performance of the proposed Management Cluster is evaluated when included as an additional layer to the Deep Learning Clusters. On average; the proposed Deep Learning cluster structure improves Smart Search performance. [ABSTRACT FROM AUTHOR]

The Cognitive Packet Network (CPN) bases its routing decisions and flow control on the Random Neural Network (RNN) Reinforcement Learning algorithm; this paper proposes the addition of a Deep Learning (DL) Cluster management structure to the CPN for Quality of Service metrics (Delay Loss and Bandwidth), Cyber Security keys (User, Packet and Node) and Management decisions (QoS, Cyber and CEO). The RNN already models how neurons transmit information using positive and negative impulsive signals whereas the proposed additional Deep Learning structure emulates the way the brain learns and takes decisions; this paper presents a brain model as the combination of both learning algorithms, RNN and DL. The proposed model has been simulated under different network sizes and scenarios and it has been validated against the CPN itself without DL clusters. The simulation results are promising; the presented CPN with DL clusters as a mechanism to transmit, learn and make packet routing decisions is a step closer to emulate the way the brain transmits information, learns the environment and takes decisions. [ABSTRACT FROM AUTHOR]

Web users are not assured that the results provided by Web search engines or recommender systems are either exhaustive, or even the most relevant to their search needs. Businesses that provide services through the web have a commercial interest to rank higher on results or recommendations to attract more customers, while Web search engines and recommender systems make a profit based on the advertisers that can offer a higher payment for their advertisements. Thus we propose a neuro-computing application that addresses these issues from the perspective of end-users. We present an Intelligent Search Assistant (ISA) that acts as an interface between the user and different search engines. Using the Random Neural Network as a learning engine that operates with learned by gradient descent and reinforcement learning, the ISA learns how to reorder results and present them to the end-user, according to the perceived relevance of the results for the end-user's benefit. We also present a new relevance metric, which combines both relevance and rank, to validate and compare the performance of our proposed solution against other Web search engines and recommender systems. The resulting rank relevance provided by different Web search engines, metasearch engines, academic databases and recommender systems are compared with the ISA, which appears to outperform commercial search tools. [ABSTRACT FROM AUTHOR]

Checkpoints are widely used to improve the performance of computer systems and programs in the presence of failures, and they significantly reduce the overall cost of running a program, if the program or the underlying system, are subject to failures. Thus application level checkpointing has been proposed for programs which may execute on platforms which are prone to failures, and also to reduce the execution time of programs which are prone to internal failures. This paper develops a mathematical model to estimate the average execution time of a program in the presence of failures, without and with application level checkpointing, and we use it to predict the optimum interval number of instructions which should be executed between the placement of successive checkpoints. The case of programs with loops and nested loops is also discussed. The results are illustrated with several numerical examples. [ABSTRACT FROM AUTHOR]