Why We Do Not Evolve Software? Analysis of Evolutionary Algorithms
arXiv:1810.07074
Abstract
In this paper, we review the state-of-the-art results in evolutionary computation and observe that we do not evolve non trivial software from scratch and with no human intervention. A number of possible explanations are considered, but we conclude that computational complexity of the problem prevents it from being solved as currently attempted. A detailed analysis of necessary and available computational resources is provided to support our findings.
References in corpus (5)
- Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
- Boltzmann brains and the scale-factor cutoff measure of the multiverse
- Unethical Research: How to Create a Malevolent Artificial Intelligence
- AI Programmer: Autonomously Creating Software Programs Using Genetic Algorithms
- On the Origin of Samples: Attribution of Output to a Particular Algorithm