search

vikasverma1077 / ICT

Code for reproducing ICT (published in Neural Networks 2022, and in IJCAI 2019)
143 stars 33 forks source link

Two Moons dataset hyperparameters #8

Closed VincentPisztora closed 4 years ago

VincentPisztora commented 4 years ago

Hi there - Thank you for posting this well organized repo! I might have missed it, but could you share the hyperparameter settings (max consistency coefficient and ramp-up schedule, beta distribution parameter, EMA rate, L2 coefficient, batch size) that were used for the two moons dataset? (Figure 1. in the paper)

Thanks!

vikasverma1077 commented 4 years ago

this should reproduce the two moons fig https://docs.google.com/document/d/1oRb6so-nXVM2ZVlOeSgHTvUgKmhqoR7TWmFvIUzJtUs/edit?usp=sharing

VincentPisztora commented 4 years ago

Thanks for the quick response! I was able to reproduce the results. Just a note - some settings were slightly different than in the paper (num./size of layers, unif distn bounded at .2)