Closed djanloo closed 2 years ago
The distribution of true - norm. estimated seems to have a linear trend.
The normalization operation requires the knowledge of the true value, but a linear trend should be the easiest to learn. Why doesn't it seem to be so?
The net does not have the true value as a reference while doing predictions. The linear trend has a deeper origin, it cannot be learned by a 1-unit dense layer. I am dumb.
The distribution of true - norm. estimated seems to have a linear trend.
The normalization operation requires the knowledge of the true value, but a linear trend should be the easiest to learn. Why doesn't it seem to be so?