News for hackers. Stuff that matters.
Re:Deep learning by onnoonno on Monday July 27, 2015 @03:00PM (#9957252)
I am rather thinking about an on/off 'object detected 'for objects with any rotation angle. That symmetry surely must be exploitable somehow in shared parameters of the DNN or similar?

My gut feeling is that the first convolutional layer's kernels, for example, would probably have a 'some are orthogonal' constraint due to this symmetry.

There are no comments on this comment yet.