News for hackers. Stuff that matters.
Re:The fraudulent claims made by IBM about Watson and AI by KRAKRISMOTT on Sunday February 05, 2023 @10:25PM (#34672938)
I am curious how that could be implemented. Given a cat/dog classifier, theoretically assuming everything is iid, an "unknown" would be equally far from either category in latent space. So in some ways, you can gate the softmax output if it's too close to 50-50. But this is more of a hack then a real solution to representing the idea of "unknown".
Re:The fraudulent claims made by IBM about Watson and AI by opportune on Sunday February 05, 2023 @11:06PM (#34673213)
By introducing the concept of “unknown” you are also introducing to the model the concept of a false positive and (if there are inputs either in training or in applying the model that are truly unknown) false negative alongside “wrong”. I think you’d want to make this assessment before applying softmax as with softmax you are only getting the relative probabilities of various classifications, when “unknown” should be done based on absolute probability - I don’t care if Bird is 100x more likely than Dog or Cat if it’s still only 1% chance.

I am not a DL genius so if I had to do this, I would probably just make “unknown” a true output and introduce some extra data / augmented data to make it a true input. I am guessing to do this the right way you would need a way to incentivize some convergence towards unknown, maybe involving some loss function looking at the false positive and false negative rate across a batch.

Re:The fraudulent claims made by IBM about Watson and AI by nothing0001 on Monday February 06, 2023 @06:31AM (#34676008)
Just make a loss function that gives +1 for correct answer, -1 for incorrect answers and 0 for unknown. Since this idea took me like 10 seconds, I suppose something like this must/should have been used before.

Unrelated, what happen when we train a model using a discontinuous function? Could the trained model be used to detect some pattern in the data?, for example if the input vector to such a model is a direct sum of two independent variables could such model be used to detect that the problem can be decomposed in two independent problems. Sorry of being off-topic and thinking aloud.