Network architecture for computing feedforward functions, including the identity function and multiplication of two input scalars.

This network extends the training network in Fig 2, represented by components with the gray background, by including an additional detailed neuron population “pop2” and the corresponding oracle components. With this architecture, we can compute the feedforward function f(x) on the connection between “pop1” and “pop2” by using osNEF to train the synaptic parameters d1, e2, and h1. As before, coloration indicates ReLU neurons (gray) or detailed neurons (blue), synaptic parameters trained by online learning (orange) or offline optimization (green), NEF computations (gray), and finally the new components involved in the calculation of f(x) (purple).