Compressive neural representation of sparse, high-dimensional probabilities thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Compressive neural representation of sparse, high-dimensional probabilities

Published on Jan 14, 20134250 Views

This paper shows how sparse, high-dimensional probability distributions could be represented by neurons with exponential compression. The representation is a novel application of compressive sensing t

Related categories

Chapter list

Compressive neural representation of sparse, high-dimensional probabilities00:00
Random perceptrons01:55
Verify information by L1 reconstruction*02:35
Compression preserves important relationships02:53