Open Access

Fig. 2

image

Example of activation function computation for a single neuron. The value of is computed from Eq. (1). The symbols have the meaning specified in Sect. 3.1. In the example shown, n = 3 (number of neurons in layer ), i = 1 (neuron considered in layer + 1), k = 1, 2, 3 (neuron identifiers for layer ). The value of becomes , which is used to compute the activation function value for neurons j in the successive layer + 2.

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.