Hacker News Reader

sorry for posting twice in this thread but i figure it's a good place to ask: what other methods are there for getting a nn to report "i don't know"

View on HN

My Master thesis supervisor had a fun trick for this, that can be used not only on on NNs, but also on other classifiers: https://arxiv.org/pdf/1011.3177.pdf

The gist is, you train a single classifier that will work as two classifiers (with certain restrictions): one that says "false/not-false" and another that says "true/not-true".

If the output of the classifier is "not-false" and "not-true", then you consider that as a "I don't know".

Is this what you mean: For example, in MNIST, your model would output 20 probabilities: (1-yes: 0.8, 1-no: 0.2, 2-yes: 0.1, 2-no: 0.9, etc) where each pair sums to 1?

Or train the network with unknown or not-a-number data or pseudo data. https://patents.google.com/patent/US5359699?oq=5%2C359%2C699

Reply on news.ycombinator.com