On the principles of Parsimony and Self-consistency for the emergence of intelligence

作     者：Yi MA Doris TSAO Heung-Yeung SHUM Yi MA;Doris TSAO;Heung-Yeung SHUM

作者机构：Electrical Engineering and Computer Science DepartmentUniversity of CaliforniaBerkeleyCA94720USA Department of Molecular&Cell Biology and Howard Hughes Medical InstituteUniversity of CaliforniaBerkeleyCA94720USA International Digital Economy AcademyShenzhen518045China 

出 版 物：《Frontiers of Information Technology & Electronic Engineering》 (信息与电子工程前沿（英文版）)

年 卷 期：2022年第23卷第9期

页      面：1298-1323页

核心收录：

学科分类：0710[理学-生物学] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Rob Fergus of New York University Microsoft Research, MSR, (2022) 

主　　题：Intelligence Parsimony Self-consistency Rate reduction Deep networks Closed-loop transcription 

摘      要：Ten years into the revival of deep networks and artificial intelligence,we propose a theoretical framework that sheds light on understanding deep networks within a bigger picture of intelligence in *** introduce two fundamental principles,Parsimony and Self-consistency,which address two fundamental questions regarding intelligence:what to learn and how to learn,*** believe the two principles serve as the cornerstone for the emergence of intelligence,artificial or *** they have rich classical roots,we argue that they can be stated anew in entirely measurable and computable *** specifically,the two principles lead to an effective and efficient computational framework,compressive closed-loop transcription,which unifies and explains the evolution of modern deep networks and most practices of artificial *** we use mainly visual data modeling as an example,we believe the two principles will unify understanding of broad families of autonomous intelligent systems and provide a framework for understanding the brain.