Mouret Jean-Baptiste
Inria, CNRS, Université de Lorraine, LORIA, Nancy 54000, France.
iScience. 2020 Oct 28;23(11):101731. doi: 10.1016/j.isci.2020.101731. eCollection 2020 Nov 20.
Evolution gave rise to creatures that are arguably more sophisticated than the greatest human-designed systems. This feat has inspired computer scientists since the advent of computing and led to optimization tools that can evolve complex neural networks for machines-an approach known as "neuroevolution." After a few successes in designing evolvable representations for high-dimensional artifacts, the field has been recently revitalized by going beyond optimization: to many, the wonder of evolution is less in the perfect optimization of each species than in the creativity of such a simple iterative process, that is, in the diversity of species. This modern view of artificial evolution is moving the field away from microevolution, following a fitness gradient in a niche, to macroevolution, filling many niches with highly different species. It already opened promising applications, like evolving gait repertoires, video game levels for different tastes, and diverse designs for aerodynamic bikes.
进化产生了一些生物，它们可以说是比最伟大的人类设计系统还要复杂。自计算技术出现以来，这一壮举启发了计算机科学家，并催生了一些优化工具，这些工具可以为机器进化出复杂的神经网络——这种方法被称为“神经进化”。在为高维工件设计可进化表示方面取得一些成功之后，该领域最近因超越优化而重新焕发生机：对许多人来说，进化的奇妙之处与其说是每个物种的完美优化，不如说是这样一个简单迭代过程的创造力，即物种的多样性。这种对人工进化的现代观点正在推动该领域从微进化（在一个生态位中沿着适应度梯度发展）转向宏进化，用高度不同的物种填充许多生态位。它已经开启了一些有前景的应用，比如进化步态库、针对不同口味的视频游戏关卡以及空气动力学自行车的多样设计。
