The unsupervised method identifies complex internal representations without human guidance
The unsupervised method identifies complex internal representations without human guidance
this is a really great example of how much clearer things look from the geometric perspective: we should really think of the classic curve detector family in inceptionv1 as points on a 'curve manifold', and the wiggles in this manifold allow readoff of different semantic information. I think this points towards why manifolds are such a useful representational strategy: by arranging its neurons to work together, it can actually represent many ideas with a single subspace
Ask a question below.
Published answers will appear here.
