Supervised neural networks are composed of parallel processing units. Each unit, called neurons, computes certain mathematical functions. The units are arranged in layers and connected by synaptic weights to balance the entries, trying to adjust them to a predetermined output pattern. The correct definition of the number of layers and the number of neurons in each layer are crucial, once the training is directly influenced by these parameters. To explore this point, data of scaling from five different regions were arranged in a spreadsheet and randomly divided into training and validation set. Data were presented for three networks with different architectures. The evaluation was performed using residual plots and t test (p <0.05). To estimate volume per tree, the neural network must be built with more than 10 neurons in the first layer, and it is recommended the use of more than one intermediate layer.
Tree scaling; Neurons; Layers
