Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Google DeepMind CEO Says Some Form of AGI Possible in a Few Years. Parent comment
Deep learning has been a series of *engineering* successes stacking over each other rather than theory being applied rigorously.
It's hard to scale training on the "dumb" approximators like a kitchen sink regression, and balancing overfitting becomes a nightmare.
There are no comments on this comment yet.
Deep learning has been a series of *engineering* successes stacking over each other rather than theory being applied rigorously.
It's hard to scale training on the "dumb" approximators like a kitchen sink regression, and balancing overfitting becomes a nightmare.