General Information Theory: Time and Information

TL;DR

This paper extends information theory by integrating time as a measure of information, unifying cognition and Shannon theory, and proposing new concepts like negative probability and information black holes to interpret physical and informational phenomena.

Contribution

It introduces a novel framework incorporating time into information theory, redefining information, and proposing new concepts to unify physical and cognitive information processes.

Findings

Law of information entropy change varies with time measure

Negative probability and information black holes explain information conservation in physics

Mutation better models neural network training processes

Abstract

This paper introduces time into information theory, gives a more accurate definition of information, and unifies the information in cognition and Shannon information theory. Specially, we consider time as a measure of information, giving a definition of time, event independence at the time frame, and definition of conditional probability. Further, we propose an analysis method of unified time measure, and find the law of information entropy reduction and increase, which indicates that the second law of thermodynamics is only the law at a certain time measure framework. We propose the concept of negative probability and information black hole to interpret the conservation of information in physics. After the introduction of time, we can give the definition of natural variation and artificial variation from the perspective of information, and point out that it is more reasonable to use the mutation to represent the neural network training process. Further, we point out the defects of the existing artificial intelligence.