News for hackers. Stuff that matters.
Re:Neural Networks That Describe Images by Zeebrommer on Thursday November 20, 2014 @05:11AM (#8635057)
I'm a bit skeptic. They have several very good examples, and those are really impressive. Everything about how often these striking results occur is 'coming soon' though. And since it is neural network-based, being lucky sometimes doesn't say anything about the statistical performance. What percentage of the test dataset was labelled correctly?
Re:Neural Networks That Describe Images by userbinator on Thursday November 20, 2014 @05:39AM (#8635136)
I'd like to see the worst-case behaviour too - e.g. hilariously wrong results. Seeing the failures (and their rate) makes it more believable and enables a more unbiased evaluation of the capabilities of the system.

It's like those "up to XX% better" claims - "up to", not "at least" being the key phrase here.

Re:Neural Networks That Describe Images by gaurav_v on Thursday November 20, 2014 @09:49AM (#8635936)
Model performance is discussed in their full paper, here:

http://cs.stanford.edu/people/karpathy/deepimagesent/devisag...