langreiter.com plain, simple: 2007-09-23-tenCat

LANGREITER.COM plain, simple

START

INDEX

2007-09-23-tenCat

CREATED BY chris • LAST EDITED BY chris 6362 days AGO

Three-quarters thru Josh Tenenbaum's ICML 2007 lecture (Bayesian Models of Human Inductive Learning). So far, really intriguing; inductive biases are necessary for learning, strong inductive biases greatly facilitate learning from very few examples (remember the old Chomskyan question?) — and, best of all, inductive biases themselves (e.g. the Shape Bias) can be learned (he cited a rather spectacular result from developmental psychology: 17-month-olds who were trained on labelling [artificial] categories of things [e.g. "wibs" and "zubs"] for 2 months [only 20 mins/week, no worries] commanded roughly twice the real-world object name vocabulary compared with their control group - while the number of other words used was comparable).