Computer Science – Computer Vision and Pattern Recognition
Scientific paper
2011-08-04
Computer Science
Computer Vision and Pattern Recognition
8 pages, 3 figures
Scientific paper
We give an algorithm that learns a representation of data through compression. The algorithm 1) predicts bits sequentially from those previously seen and 2) has a structure and a number of computations similar to an autoencoder. The likelihood under the model can be calculated exactly, and arithmetic coding can be used directly for compression. When training on digits the algorithm learns filters similar to those of restricted boltzman machines and denoising autoencoders. Independent samples can be drawn from the model by a single sweep through the pixels. The algorithm has a good compression performance when compared to other methods that work under random ordering of pixels.
Gregor Karol
LeCun Yann
No associations
LandOfFree
Learning Representations by Maximizing Compression does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Learning Representations by Maximizing Compression, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning Representations by Maximizing Compression will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-15089