학술논문

Information Flow Decomposition in Feedback Systems: General Case Study
Document Type
Working Paper
Source
Subject
Computer Science - Information Theory
Language
Abstract
We derive three fundamental decompositions on relevant information quantities in feedback systems. The feedback systems considered in this paper are only restricted to be causal in time domain and the channels are allowed to be subject to arbitrary distribution. These decompositions comprise the well-known mutual information and the directed information, and indicate a law of conservation of information flows in the closed-loop network.
Comment: 10 pages, 1 figure. Seminar Report