Jump3 is a net with 3 inputs and two hidden neurons. The hidden neurons and the output neuron all use the hyperbolic tangent activation function (therefore the output signal is –1 to 1). There are extra (jump) connections from the input neurons to the output neuron, as well as a connection from the first hidden neuron to the second.

scale – the number of past bars over which input scaling will take place. Recommended optimizer range is 10 to 200.

input1 to input3  -  neural network inputs. Indicators such as Price Momentum indicators are recommended. Let the optimizer find the parameters for the indicators.

w1 to w12 – the weights in the neural network. These are similar to coefficients in regression analysis. Recommended optimizer range is –1 to 1.