Can anyone help with understanding how to best do #modelselection in the context of #neuralnetworks ? I'm trying to understand how to reduce #bias due to the selection of a particular test set.
More details here
#neuralnetworks #modelselection #bias
Our paper "Sequential Bayesian Learning for Hidden Semi-Markov Models", joint work of Konstantinos Kalogeropoulos and me, is now available on ArXiv: https://arxiv.org/abs/2301.10494
#hsmm #smc #mcmc #clustering #modelselection
7/10) This finding led to our #proposal: Can we use α for #modelSelection in an #SSL pipeline?
Two key +s of α:
1. α doesn’t require labels
2. α is quick to #compute (compared to training a readout)
We study hyperparam selection in #BarlowTwins (Zbontar et al.) as a case study!
#neuroscience #deeplearning #ml #ai #barlowtwins #compute #ssl #modelselection #proposal