We show that passing input points through a simple Fourier feature mapping enables a multilayer perceptron (MLP) to learn high-frequency functions in low-dimensional problem domains. These results ...

We show that passing input points through a simple Fourier feature mapping enables a multilayer perceptron (MLP) to learn high-frequency functions in low-dimensional problem domains. These results ...

Function y = cos(x) calculates the cosine of an angle in radians. It has a high-speed, fully pipelined architecture and uses a polynomial with dynamic coefficients to calculate the result to within ...