Nie jesteś zalogowany | zaloguj się

Wydział Matematyki, Informatyki i Mechaniki Uniwersytetu Warszawskiego

  • Skala szarości
  • Wysoki kontrast
  • Negatyw
  • Podkreślenie linków
  • Reset

Aktualności — Wydarzenia

Sem. "Uczenie maszynowe"


One Simple Trick to Fix Your Bayesian Neural Network

Prelegent: Piotr Tempczyk

2022-11-03 12:15

One of the most popular estimation methods in Bayesian neural networks (BNN) is mean-field variational inference (MFVI). In this work, we show that neural networks with ReLU activation function induce posteriors, that are hard to fit with MFVI. We provide a theoretical justification for this phenomenon, study it empirically, and report the results of a series of experiments to investigate the effect of activation function on the calibration of BNNs. We find that using Leaky ReLU activations leads to more Gaussian-like weight posteriors and achieves a lower expected calibration error (ECE) than its ReLU-based counterpart.