Gödel Incompleteness Theorem for PAC Learnable Theory from the view of complexity measurement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Zhifeng, Wu, Tianyi, Han, Zhangang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915153501487104
author Ma, Zhifeng
Wu, Tianyi
Han, Zhangang
author_facet Ma, Zhifeng
Wu, Tianyi
Han, Zhangang
contents Different from the view that information is objective reality, this paper adopts the idea that all information needs to be compiled by the interpreter before it can be observed. From the traditional complexity definition, this paper defines the complexity under "the interpreter", which means that heuristically finding the best interpreter is equivalent to using PAC to find the most suitable interpreter. Then we generalize the observation process to the formal system with functors, in which we give concrete proof of the generalized Gödel incompleteness theorem which indicates that there are some objects that are PAC-learnable, but the best interpreter is not found among the alternative interpreters. A strong enough machine algorithm cannot be interpretable in the face of any object. There are always objects that make a strong enough machine learning algorithm uninterpretable, which puts an upper bound on the generalization ability of strong AI.
format Preprint
id arxiv_https___arxiv_org_abs_2408_10211
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gödel Incompleteness Theorem for PAC Learnable Theory from the view of complexity measurement
Ma, Zhifeng
Wu, Tianyi
Han, Zhangang
Logic in Computer Science
Logic
Different from the view that information is objective reality, this paper adopts the idea that all information needs to be compiled by the interpreter before it can be observed. From the traditional complexity definition, this paper defines the complexity under "the interpreter", which means that heuristically finding the best interpreter is equivalent to using PAC to find the most suitable interpreter. Then we generalize the observation process to the formal system with functors, in which we give concrete proof of the generalized Gödel incompleteness theorem which indicates that there are some objects that are PAC-learnable, but the best interpreter is not found among the alternative interpreters. A strong enough machine algorithm cannot be interpretable in the face of any object. There are always objects that make a strong enough machine learning algorithm uninterpretable, which puts an upper bound on the generalization ability of strong AI.
title Gödel Incompleteness Theorem for PAC Learnable Theory from the view of complexity measurement
topic Logic in Computer Science
Logic
url https://arxiv.org/abs/2408.10211