Hyperparameter optimization in ML Replacing a hyperparameter problem with a hyperhyperparameter problem which feels like progress I guess 2020-09-25 – 2020-09-28
AutoML 2017-07-17 – 2020-09-25
Free energy Fancy analogy for understanding cognition 2011-11-27 – 2019-12-11
Informations Entropies and other measures of surprise 2011-11-25 – 2019-09-10
Ergodic theory / mixing For things that probably happen eventually instead of just probably 2011-10-17 – 2018-10-23
Statistical learning theory Eventually including structural risk minimisation, risk bounds, hopefully-uniform convergence rates, VC-dimension, generalisation-and-stability framings etc 2016-07-06 – 2016-08-16