An
essential characteristic of NEF is the ability to represent
high-dimensional mathematical constructs with high-dimensional neurons.
OZ neurons can be driven with high-dimensional signals (using few
weighted inputs), featuring high-dimensional tuning . The analog
learning system schematic is shown in Figure 4, A . By setting a
similar weight for the two incoming signals, we derive the neuron’s
tuning shown in Figure 4, B . We used the circuit described inFigure 4, A, with eight 2D spiking neurons to represent a 2D
signal, wherein one dimension follows an exponentially rising signal and
the other, a sinusoidal wave. Representation results are shown inFigure 4, C, and the error traces are shown in Figure
4, D .
Transformation