An Algorithmic Refinement of Maxent Induces a Thermodynamic-like Behaviour in the Reprogrammability of Generative Mechanisms

05/18/2018
by   Hector Zenil, et al.
0

Reprogramming a generative mechanism to produce a different object is associated with a cost. Here we use the notion of algorithmic randomness to quantify such a cost when reprogramming networks. We identify an asymmetry in a measure of reprogrammability, suggesting an analogy with a thermodynamic asymmetry. The principle of maximum entropy (Maxent) quantifies the evolution of entropy or the uncertainty during state transitions in systems confined to an equilibrium condition. Here we define a generalisation based on algorithmic randomness not restricted to equilibrium physics, based on both distance to algorithmic randomness and reprogrammability. We advance a constructive preferential attachment algorithm approximating a maximally algorithmic random network. Hence, as a refinement on classical Maxent, networks can be quantified with respect to their distance to a maximally algorithmic random network. Our analysis suggests that the reprogrammability asymmetry originates from its non-monotonic relationship to algorithmic randomness. Our analysis motivates further work on the degree of algorithmic asymmetries in systems depending on their reprogrammability capabilities.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/08/2018

On the close interaction between algorithmic randomness and constructive/computable measure theory

This is a survey of constructive and computable measure theory with an e...
research
02/12/2011

Algorithmic Randomness as Foundation of Inductive Reasoning and Artificial Intelligence

This article is a brief personal account of the past, present, and futur...
research
10/01/2019

Non-algorithmic theory of randomness

This paper proposes an alternative language for expressing results of th...
research
12/22/2017

Practical Implementation of a Deep Random Generator

We have introduced in former work the concept of Deep Randomness and its...
research
05/10/2020

Maximal Algorithmic Caliber and Algorithmic Causal Network Inference: General Principles of Real-World General Intelligence?

Ideas and formalisms from far-from-equilibrium thermodynamics are ported...
research
05/08/2020

Measuring the Algorithmic Efficiency of Neural Networks

Three factors drive the advance of AI: algorithmic innovation, data, and...
research
08/03/2022

Local time of Martin-Lof Brownian motion

In this paper we study the local times of Brownian motion from the point...

Please sign up or login with your details

Forgot password? Click here to reset