Re:The Limitations of Deep Learning
by webmaven on Monday July 17, 2017 @11:20PM
(#14794063)
So, time's arrow can be reversed, and the model can thus extrapolate both forward and backward. Cool!
However, that doesn't actually eliminate the axis/dimension. Eliminating timestamps only makes the dimension a unitless scalar (IOW 'time' tautologically increments at a 'rate' of 'one frame per frame').
However, that doesn't actually eliminate the axis/dimension. Eliminating timestamps only makes the dimension a unitless scalar (IOW 'time' tautologically increments at a 'rate' of 'one frame per frame').