The Role of Evolution in Machine Intelligence

06/21/2021
by   Awni Hannun, et al.
0

Machine intelligence can develop either directly from experience or by inheriting experience through evolution. The bulk of current research efforts focus on algorithms which learn directly from experience. I argue that the alternative, evolution, is important to the development of machine intelligence and underinvested in terms of research allocation. The primary aim of this work is to assess where along the spectrum of evolutionary algorithms to invest in research. My first-order suggestion is to diversify research across a broader spectrum of evolutionary approaches. I also define meta-evolutionary algorithms and argue that they may yield an optimal trade-off between the many factors influencing the development of machine intelligence.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/30/2018

Inheritance-Based Diversity Measures for Explicit Convergence Control in Evolutionary Algorithms

Diversity is an important factor in evolutionary algorithms to prevent p...
research
06/10/2013

Using the quaternion's representation of individuals in swarm intelligence and evolutionary computation

This paper introduces a novel idea for representation of individuals usi...
research
08/19/2016

Haploid-Diploid Evolutionary Algorithms

This paper uses the recent idea that the fundamental haploid-diploid lif...
research
06/03/2019

2019 Evolutionary Algorithms Review

Evolutionary algorithm research and applications began over 50 years ago...
research
07/02/2009

Evidence of coevolution in multi-objective evolutionary algorithms

This paper demonstrates that simple yet important characteristics of coe...
research
06/01/2011

Evolution of Things

Evolution is one of the major omnipresent powers in the universe that ha...
research
01/20/2014

Análisis e implementación de algoritmos evolutivos para la optimización de simulaciones en ingeniería civil. (draft)

This paper studies the applicability of evolutionary algorithms, particu...

Please sign up or login with your details

Forgot password? Click here to reset