News for hackers. Stuff that matters.
Re:AI Models Predict Breast Cancer with Radiologist-Level Ac... by baq on Tuesday June 25, 2019 @03:19PM (#20277842)
remember when ensembles were the cool word before they got erased from collective consciousness and replaced with deep things? it can't even be a decade, was it 2012 or something?
Re:AI Models Predict Breast Cancer with Radiologist-Level Ac... by krisoft on Tuesday June 25, 2019 @05:18PM (#20279061)
They haven't got erased, but more like subsumed? If you use dropout to train your model that is basically equivalent with using an ensemble of deep neural networks.
Re:AI Models Predict Breast Cancer with Radiologist-Level Ac... by irq11 on Wednesday June 26, 2019 @12:13AM (#20281844)
That is not even close to the same thing.

If you train an ensemble of models with random dropout, you have an ensemble. Models trained with dropout will still have significant variation from run to run.

Re:AI Models Predict Breast Cancer with Radiologist-Level Ac... by sooheon on Wednesday June 26, 2019 @12:24AM (#20281903)
> That is not even close to the same thing.

It's a common interpretation: https://arxiv.org/abs/1706.06859

Re:AI Models Predict Breast Cancer with Radiologist-Level Ac... by irq11 on Wednesday June 26, 2019 @06:53PM (#20290099)
There may be a paper on it, but it’s not a common view.

In particular, this paper neglected to do the obvious thing: ensemble networks trained with dropout. It improves performance over dropout alone.

Re:AI Models Predict Breast Cancer with Radiologist-Level Ac... by rerx on Tuesday June 25, 2019 @06:00PM (#20279472)
Why shouldn't you employ an ensemble of deep neural networks?
Re:AI Models Predict Breast Cancer with Radiologist-Level Ac... by salty_biscuits on Wednesday June 26, 2019 @01:39AM (#20282177)
Correlated errors. Naive averaging will lead to overconfidence and it is not trivial to model the correlation. Boosting is worth a shot though.
Re:AI Models Predict Breast Cancer with Radiologist-Level Ac... by rerx on Thursday June 27, 2019 @12:50PM (#20296161)
My point was that ensembles of deep neural networks are commonly used and yield higher accuracies.
Re:AI Models Predict Breast Cancer with Radiologist-Level Ac... by AstralStorm on Wednesday June 26, 2019 @03:51AM (#20282738)
More importantly, what happens if you put a radiologist opinion (or multiple) in such an ensemble?