the proposed iafc neural networks have both stability and plasticity because theyuse a control structure similar to that of the art-1(adaptive resonance theory) neural network.the unsupervised iafc neural network is the unsupervised neural network which uses the fuzzyleaky learning rule. this fuzzy leaky learning rule controls the updating amounts by fuzzymembership values. the supervised iafc ...

in recent years, researches on reinforcement learning (rl) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. neural network reinforcement learning (nnrl) is among the most popular algorithms in the rl framework. the advantage of using neural networks enables the rl to search for optimal policies more efficiently in several real-life applicat...

this paper aims to assess the quality and accuracy aster dems and the arcgis alogorthms used for hydrologic analyses. to this end, first the plan of drainage networks in the region was extracted from aerial photographs and high resolution satellite images and was set as the real ground. in the next step, using the hydrology tool in arcgis software, raster networks of the region for the whole ca...

in recent years mobile networks have expanded dramatically, compared with other wireless networks. routing protocols in these networks are designed with the assumption that there is no attacker node, so routing protocols are vulnerable to various attacks in these networks. in this paper, we review the network layer attacks and then we simulate the impact of black hole attack on ad hoc on demand...

the environmental rules of reverse logistic networks have caused important economic growth in the past decades. to integrate forward logistic networks with reverse logistics networks a helpful method is to design both networks simultaneously. considering more retrieval choices in modeling reverse logistic systems can be very critical. this article contains a mixed integer linear programming mod...

book social media are reading communities primarily developed as online social networks. this study aims to find precise criteria and indicators for evaluation of book social network and examine and rank the most popular book social networks. the sample population included 10 english and two persian book/reading social networks publicly available on the web. a checklist containing 9 main criter...

this article is a comparative study of estimation power of artificial neural networks and autoregressive time series models in inflation forecasting. using 37 years iran’s inflation data, neural networks performs better on average for short horizons than autoregressive models. this study shows usefulness of early stopping technique in learning stage of neural networks for estimating time series...

Considering the network structure is one of the new approaches in studying stochastic PERT networks (SPN). In this paper, planar networks are studied as a special class of networks. Two structural reducible mechanisms titled arc contraction and deletion are developed to convert any planar network to a series-parallel network structure.&#10In series-parallel SPN, the completion time distribution...

background: this study aimed to evaluated trends for iron and manganese concentrations in wells, reservoirs, and water distribution networks in qom city during the summer of 2012. methods: this was a cross-sectional study. the studied scopes consisted of groundwater (60 wells), reservoirs (10 tanks), and water distribution network (33 points). one sample was taken from each source monthly. stat...