neuralnetworks.calculate

(cost-fn input output error-fn sigmoid-fn lambda thetas-dimensions)

(delta input thetas activation-nodes output sigmoid-fn)

Calculate the ‘error’ (delta) from the expected input/output for the given thetas. This will also calculate the delta for each hidden layers.

(forward-propagate input thetas sigmoid-fn)

Will return list of activation nodes for each theta

(output-nodes input theta sigmoid-fn)

(reshape-thetas thetas thetas-dimensions)

Reshapes theta vectors based on the given thetas-dimensions where thetas-dimensions are vector of matrices dimensions

(theta-gradient deltas thetas lambda input-count)

Generated by Codox