News for hackers. Stuff that matters.
Re:Using deep learning to listen for whales by daviddumenil on Friday January 10, 2014 @10:56AM (#7037217)
Converting it to a spectrogram was a nice step.

From the perspective of other source data, I wonder if that limits you to five features (X,Y and RGB) or whether you could extend to fictional/non-human-visible colours as extra features and just be unable to view them in the weight maps.

Re:Using deep learning to listen for whales by cdash on Friday January 10, 2014 @12:08PM (#7037755)
It mentions in the article that the spectrogram is really grayscale instead of having RGB channels.
Re:Using deep learning to listen for whales by dnouri on Friday January 10, 2014 @11:19AM (#7037353)
An interesting idea. Yes, you can usually use a convnet with any number of channels per pixel.