Information Bottleneck Approach to Predictive Inference
This paper synthesizes a recent line of work on automated predictive model making inspired by Rate-Distortion theory, in particular by the Information Bottleneck method. Predictive inference is interpreted as a strategy for efficient communication. The relationship to thermodynamic efficiency is dis...
Main Author: | Susanne Still |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2014-02-01
|
Series: | Entropy |
Subjects: | |
Online Access: | http://www.mdpi.com/1099-4300/16/2/968 |
Similar Items
-
Mesoscopic Thermodynamics for the Dynamics of Small-Scale Systems
by: J. Miguel Rubi
Published: (2015-10-01) -
Markov Information Bottleneck to Improve Information Flow in Stochastic Neural Networks
by: Thanh Tang Nguyen, et al.
Published: (2019-10-01) -
Estimating Predictive Rate–Distortion Curves via Neural Variational Inference
by: Michael Hahn, et al.
Published: (2019-06-01) -
On the Difference between the Information Bottleneck and the Deep Information Bottleneck
by: Aleksander Wieczorek, et al.
Published: (2020-01-01) -
Function Identification in Neuron Populations via Information Bottleneck
by: S. Kartik Buddha, et al.
Published: (2013-05-01)