NEOct 12, 2018

Why We Do Not Evolve Software? Analysis of Evolutionary Algorithms

arXiv:1810.07074v19 citations
Originality Synthesis-oriented
AI Analysis

This addresses a fundamental limitation in automated software generation for researchers in evolutionary computation and AI, but it is incremental as it reviews and analyzes existing challenges rather than proposing a new solution.

The paper analyzes why evolutionary algorithms have not succeeded in evolving non-trivial software from scratch without human intervention, concluding that computational complexity is the primary barrier based on a detailed resource analysis.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes