跨动物物种的集体行为。
Collective behaviour across animal species.
作者信息
DeLellis Pietro, Polverino Giovanni, Ustuner Gozde, Abaid Nicole, Macrì Simone, Bollt Erik M, Porfiri Maurizio
机构信息
1] Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples 80125, Italy [2] Department of Mechanical and Aerospace Engineering, Polytechnic School of Engineering, New York University, Brooklyn, New York 11201, USA.
Department of Mechanical and Aerospace Engineering, Polytechnic School of Engineering, New York University, Brooklyn, New York 11201, USA.
出版信息
Sci Rep. 2014 Jan 16;4:3723. doi: 10.1038/srep03723.
We posit a new geometric perspective to define, detect, and classify inherent patterns of collective behaviour across a variety of animal species. We show that machine learning techniques, and specifically the isometric mapping algorithm, allow the identification and interpretation of different types of collective behaviour in five social animal species. These results offer a first glimpse at the transformative potential of machine learning for ethology, similar to its impact on robotics, where it enabled robots to recognize objects and navigate the environment.
我们提出了一种新的几何视角，以定义、检测和分类各种动物物种集体行为的内在模式。我们表明，机器学习技术，特别是等距映射算法，能够识别和解释五种群居动物物种中不同类型的集体行为。这些结果初步展示了机器学习在动物行为学方面的变革潜力，类似于其对机器人技术的影响，即机器学习使机器人能够识别物体并在环境中导航。
Zotero 插件