Physics – Data Analysis – Statistics and Probability
Scientific paper
2000-04-24
Physics
Data Analysis, Statistics and Probability
Scientific paper
We define the relevant information in a signal $x\in X$ as being the information that this signal provides about another signal $y\in \Y$. Examples include the information that face images provide about the names of the people portrayed, or the information that speech sounds provide about the words spoken. Understanding the signal $x$ requires more than just predicting $y$, it also requires specifying which features of $\X$ play a role in the prediction. We formalize this problem as that of finding a short code for $\X$ that preserves the maximum information about $\Y$. That is, we squeeze the information that $\X$ provides about $\Y$ through a `bottleneck' formed by a limited set of codewords $\tX$. This constrained optimization problem can be seen as a generalization of rate distortion theory in which the distortion measure $d(x,\x)$ emerges from the joint statistics of $\X$ and $\Y$. This approach yields an exact set of self consistent equations for the coding rules $X \to \tX$ and $\tX \to \Y$. Solutions to these equations can be found by a convergent re-estimation method that generalizes the Blahut-Arimoto algorithm. Our variational principle provides a surprisingly rich framework for discussing a variety of problems in signal processing and learning, as will be described in detail elsewhere.
Bialek William
Pereira Fernando C.
Tishby Naftali
No associations
LandOfFree
The information bottleneck method 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 The information bottleneck method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The information bottleneck method will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-601730