Fig. 2From: Protein secondary structure prediction using a small training set (compact model) combined with a Complex-valued neural network approachThe Architecture of FCRN. The FCRN consists of a first layer of m input neurons, a second layer of K hidden neurons and a third layer of n output neurons. For the SS prediction problem presented in this work, m=27, n=3 and K is allowed to vary. The hyperbolic secant (sech) activation function computes the hidden response (\({h^{t}_{l}}\)) and the predicted output \(\widehat {y}_{l}^{t}\) is given by the exponential function. w nK represents the weight connecting the Kth hidden neuron to the nth output neuronBack to article page