This is an old revision of the document!
Environmental Machine Learning
research thread:
Boskoi 2010 > Augmented Ecology 2014 > Machine Wilderness 2015 > Environmental Machine Learning (2018?)
potential starting questions:
- if/how the concept of the 'umwelt' in biological creatures relates to the 'world view' (as Memo Akten called it) that forms in artificial neural networks during training.
- how do animals, plants or machines learn through experience and exposure?
- how much of us humans permeates into the robotic eye of the beholder? (Or more broadly: Do we hold on to us being the human?)
- can these 'synthetic' worldviews give us fresh perspectives on our environment and the lives that creatures live there?
- how do strategies of environmental observation compare/relate in AI, choreography, ecology, art, landscaping, traditional practices, etc..
- can machine learning expand environmental literacy in technology/society?
methods:
- fieldwork: exploration through interactions between man-machine-environment in-situ
- prototyping
- critical reflection
- multimodal and transdisciplinary approach: could the project also give room to explore observation strategies from various domains of human inquiry and probe them in-situ?
reading:
- “Adoption of Machine Learning Techniques in #Ecology and Earth Science. Thessen [2016]” » https://t.co/D1hOba8AY7
- “Machine Learning without Tears: A primer for Ecologists. Olden et al [2008]” » https://t.co/N1l1JKYqqh
- “Applications of machine learning in animal behaviour studies” > http://www.sciencedirect.com/science/article/pii/S0003347216303360