Stephen Downes

Knowledge, Learning, Community
It's nice to read some cracking sharp commentary about the biases that tend us toward some type of (scientific) theory rather than another. Simplicity, for example, is something we tend to favour - but there is no good reason to believe that simple theories are more likely to be true. Turney says, 'instead of asking how to measure the complexity/simplicity of a theory, we should ask which inductive biases tend to work well in this particular universe in which we find ourselves." Quite right, and I agree with Turney here (section s). Via daniel Lemire, who spends his time reading good blogs rather than attending dull meetings.

Today: 1058 Total: 1061 [Direct link] [Share]

Image from the website


Stephen Downes Stephen Downes, Casselman, Canada
stephen@downes.ca

Copyright 2024
Last Updated: Mar 29, 2024 08:29 a.m.

Canadian Flag Creative Commons License.

Force:yes