Free Access

Fig. 1


Left:structure of a neuronal unit. Each neuron implements a linear combination (using weights wi and a bias b) of its input x followed by anonlinear activation function a(x). Right: ANNstructure. Neurons in the same layer all receive the same input. The stacking of layers allows the ANN to define a model parametrized by the weight variables of the network.

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.