7 events
when toggle format what by license comment
May 4 '17 at 19:31 answer yr91 timeline score: 2
Jul 1 '16 at 19:14 answer yobibyte timeline score: 1
Jun 2 '16 at 18:02 comment added R.M. You may want to look into the literature on "Outlier detection"/"Anomaly detection" -- that's basically what you're trying to do. You have a set of know items, and you want to see if the new item fits in with the previous items, or is an outlier/anomaly.
Jun 2 '16 at 17:43 comment added Sycorax I don't see why not. I'm not an imaging expert, but the procedure under the hood for the output layer of most ANNs applied to MNIST and other machine vision tasks like that is just 'what ranks highest among possible objects?'
Jun 2 '16 at 17:33 comment added Auxiliary So it should be okay to use it as an image similarity measure, right? Provided that its training input includes a measure of how good of a face it is for example.
Jun 2 '16 at 17:29 comment added Sycorax This is basically what object recognition does. "This is a face (p>0.9)."
Jun 2 '16 at 15:49 history asked Auxiliary CC BY-SA 3.0