A critical issue of Neural Network based large-scale data mining algorithms is how to speed up their learning algorithm. This problem is particularly challenging for Error Back-Propagation (EBP) algorithm in Multi-Layered Perceptron (MLP) Neural Networks due to their significant applications in many scientific and engineering problems. In this paper, we propose an Adaptive Variable Learning Rate EBP algorithm to attack the challenging problem of reducing the convergence time in an EBP algorithm, aiming to have a highspeed convergence in comparison with standard EBP algorithm. The idea is inspired from adaptive filtering, which leaded us into two semi-similar methods of calculating the learning rate. Mathematical analysis of AVLR-EBP algorithm confirms its convergence property. The AVLR-EBP algorithm is utilized for data classification applications. Simulation results on many well-known data sets shall demonstrate that this algorithm reaches to a considerable reduction in convergence time in comparison to the standard EBP algorithm. The proposed algorithm, in classifying the IRIS, Wine, Breast Cancer, Semeion and SPECT Heart datasets shows a reduction of the learning epochs relative to the standard EBP algorithm.
Given a set of observations or new information, agents should be able to update their understandings of the world. As a part of any agents' world ontology, concepts need to evolve in time. In this paper we present a new representation for non-unanimous concepts based on the combination of feature-values and their probabilities. This representation leads us to incrementally evolve the concepts upon facing with new observations or information. As agents' access to the knowledge structure of the peer agents is limited due to the high cost of communication, we enabled our agents to use any queried object and update the previously calculated probability of every feature-value combination based on the probability of that object being an instance of a concept.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.