Re:Why train when you can optimize?
by yobbo on Saturday April 30, 2022 @01:11AM
(#31213507)
It can, but sin(x) has infinite number of extremes, and the gradients will vanish at those points. Activations will get stuck at 1 and -1 (x=π/2, 3π/2, ...). They set x+(1/a)*sin²(x) to be monotonic, which fixes this.
Or you need to optimize without using gradients.