info:eu-repo/semantics/conferenceProceedings 2016 https://unilib.phaidrabg.rs/o:1645 Krtolica, Ivana Obradović, Đorđe Cvijanović, Dušanka Kaplar, Aleksandar Živković, Milica Teodorović, Ivana Vojinović-Miloradov, Mirjana BEING SMART IN A MULTI-STRESSED WORLD - PREDICTING THE STRESS IMPACT ON Lemna minor L., Ceratophyllum demersum L. AND Mentha aquatica L. ALONG THE DANUBE RIVER USING ANN TRAINED ALGORITHMS application/pdf 123502 bytes eng From practical standpoint, ANNs are a parallel processing systems that consists of simple processing units, neurons, and directed, weighted connections between them. Artificial neural networks (ANNs) can be characterized as computational models, inspired by information processing capabilities of biological neural networks. They can be used for modeling complex interactions in natural systems. In this study a feed - forward artificial neural network with backpropagation training algorithm is used to extract relationships between land use and three selected aquatic Lemna minor L. and Ceratophyllum demersum and semiaquatic Mentha aquatica L species. BEING SMART IN A MULTI-STRESSED WORLD - PREDICTING THE STRESS IMPACT ON Lemna minor L., Ceratophyllum demersum L. AND Mentha aquatica L. ALONG THE DANUBE RIVER USING ANN TRAINED ALGORITHMS All rights reserved