Re:Artificial Intelligence Needs a Bullshit Meter
by nl on Thursday July 07, 2016 @02:01AM
(#12047700)
The established solution here is to make sure your test data actually resembles the data you intend the algorithms to work on.
That's an ideal solution, yes.
But in practice - especially for deep neural networks that take weeks to train on pretty significant hardware - most people use pre-trained models, and attempt to retrain the last layer[1].
The other issue is of course the large amounts of supervised training data needed.
That's an ideal solution, yes.
But in practice - especially for deep neural networks that take weeks to train on pretty significant hardware - most people use pre-trained models, and attempt to retrain the last layer[1].
The other issue is of course the large amounts of supervised training data needed.
[1] eg https://www.tensorflow.org/versions/r0.9/how_tos/image_retra...