News for hackers. Stuff that matters.

A comment on Feature Visualization: How neural nets build up their understanding of images. Parent comment

Re:Feature Visualization: How neural nets build up their und... by breckinloggins on Tuesday November 07, 2017 @02:02PM (#15646389)
Many of the visualizations seem interpretable even though they are (essentially, I presume) projections of a very high dimensional space onto 2d position + 3d color space. Is there any research on projecting these visualizations into 6-dimensions as well (3d position + 3d color in VR) or even higher dimensions by substituting other sensory modalities for extra spacial or color dimensions?
[ Parent | on HN ]
Re:Feature Visualization: How neural nets build up their und... by shancarter on Tuesday November 07, 2017 @02:18PM (#15646547)
I suspect the extra fidelity won't have much payoff for high dimensions considering the large cognitive overhead required for a person to make sense of it. Even a six dimensional approximation of a 1,000 dimensional space is quite crude, and we're pretty confused by spaces larger than three.
[ Parent | on HN ]