Deep learning for visual question answering: demo with Keras code

Re:Deep learning for visual question answering: demo with Ke... by tachyonbeam on Tuesday April 05, 2016 @04:46PM (#11434260)

It's not based on a bayesian system, it's a neural network that does question answering. There are no logical constraints in there. Subtly different wordings of the question could produce different answers, even if the meaning is the same.

[ Parent | on HN ]

Re:Deep learning for visual question answering: demo with Ke... by harperlee on Tuesday April 05, 2016 @04:54PM (#11434341)

I know, my point is that there doesn't seem to be a part of the system in which the two sports are weighted against, and one consistently outweights the other one. So the model is so sensible that even with exactly the same image, and the same target (identifying this as soccer), you get wild variations by changing the question - and the question not even providing a clear bias.

[ Parent | on HN ]