"change in the heritable characteristics of biological populations over successive generations " (Wikipedia). For posts about machine learning look here. See also: Biology, Evolutionary Psychology,
Firstly, evolution is a useful case study of
humans' ability (or inability) to model the real world. This is because it has a single clear criterion ("relative reproductive fitness") which is selected (optimized) for: "
can't see clearly the result of a single monotone optimization criterion—if we can't even train ourselves to hear a single pure note—then how will we listen to an orchestra? How will we see that "Always be selfish" or "Always obey the government" are poor guiding principles for human beings to adopt—if we think that even optimizing genes for inclusive fitness will yield organisms which sacrifice reproductive opportunities in the name of social resource conservation?
To train ourselves to see clearly, we need simple practice
cases" -- Eliezer Yudkowsky, Fake Optimisation Criteria
Secondly, much of rationality necessarily revolves around the human brain (for now). An understanding of how it came into being can be very helpful both for understanding
'bugs' in the system (like superstimuli), and for explaining Complexity of Value, among others.
A candy bar is a superstimulus: it contains more concentrated sugar, salt, and fat than anything that exists in the ancestral environment.
A candy bar matches taste buds that evolved in a hunter-gatherer environment, but it matches those taste buds much more strongly than anything that actually existed in the hunter-gatherer environment. The signal that once reliably correlated to healthy food has been hijacked, blotted out with a point in tastespace that wasn't in the training dataset - an impossibly distant outlier on the old ancestral graphs.
-- Eliezer Yudkowsky, Superstimuli and the Collapse of Western Civilisation