Predict Temperature of Evaporation using Neuronal network
$100-200 USD
Pago na entrega
According to Cybenko's theorem any nonlinear function can be approximated by the equivalent of a single layer Multilayer Perceptron.
The purpose of this lab is to become familiar with the use of PMCs for approximating nonlinear functions using C # and Visual Studio to enable online use of the proposed model.
The work will consist in designing a PMC able to model the behaviour of the exchanger, choose an appropriate topology, learn the PMC network with one or more hidden layers (Justify the choice), to the nonlinear function assigned.
The results and conclusions must be clear.
??? The choice of inputs and outputs of the network
??? The choice of network topology
??? The justification for choosing the learning method
??? The learning and test results
Pairs and parameter to predict:
Temperature evap (T_evap)
All what is needed is an interface that we enter a monthly data of temperature of evaporation and it can predict futur values
ID do Projeto: #3062425