[lucastx]

Fluid Concepts and Creative Analogies is a wonderful book. I wouldn't call the systems they build upon (such as lMetacat [1] and Tabletop [2]) "machine learning"...

[1] http://science.slc.edu/jmarshall/metacat/

[2] https://deepblue.lib.umich.edu/handle/2027.42/105891

I'd also like to see FARGonauts / Center for Research on Concepts and Cognition style software implementations around... I have run with success this python implementation of Copycat:

https://github.com/ajhager/copycat

[ehudla]

The original version in Common Lisp is also available: http://web.cecs.pdx.edu/~mm/how-to-get-copycat.html

[jalanb]

I implemented it in Python (while reading from that LISP version, a Java version, and Melanie Mitchell's "Analogy-Making as Perception"): https://github.com/jalanb/co.py.cat

[emmelaich]

A link on the book for other ignoramuses like me. Dunno how I've never heard of it.

(It's also by Douglas Hofstadter.)

https://en.wikipedia.org/wiki/Fluid_Concepts_and_Creative_An...

[dnautics]

Its maybe a matter of taste but I find his other work to be rather pretentious, although geb is entertaining and somewhat useful (I half liked le ton beau de marot).

I really think k there's something useful.in fluid concepts that maybe can help with low data learning. I think geoffrey Hinton hints at it in his lecture about trying to do pca on learned neural states to find manyfold correlations which in high dimensional states are stronger to be nonrandom.