I wouldn't say I changed my mind, but I substantially increased my p-estimate that the following recipe could produce something very close to intelligence:
1) a vast unlabeled data set (think 1e8 hours of video and audio/speech data plus the text of every newspaper article and novel ever written)
2) a simple unsupervised learning rule (e.g. the reduced Boltzmann machine rule)
3) a huge computer network capable of applying many iterations of the rule to the data set.
I previously believed that such an approach would fail because it would be very difficult to "debug" the resulting networks. Now I think that might just not matter.
Admitting to being wrong isn't easy, but it's something we want to encourage.
So ... were you convinced by someone's arguments lately? Did you realize a heated disagreement was actually a misunderstanding? Here's the place to talk about it!