Re:Listening for illegal logging chainsaws using TensorFlow
by coolio2657 on Friday March 23, 2018 @02:10PM
(#16660967)
I know this is a digression from the current discussion on how well the devices work, but as a stats student who just learned about estimating using log-likelihoods, could you give some more info on how that is inferior to the Bayesian model (since I've heard the exact opposite is true)?
[ Parent
| on HN ]
Re:Listening for illegal logging chainsaws using TensorFlow
by tonic_section on Friday March 23, 2018 @02:21PM
(#16661095)
The problem is that neural networks trained using maximum LL do not return calibrated probabilities, using e.g. the softmax output as 'confidence' of a model tends to result in overconfident predictions, take a look at adversarial attacks on neural networks for an extreme example: https://blog.openai.com/adversarial-example-research/