2 code implementations • 2 Nov 2018 • Pawel Chilinski, Ricardo Silva
We leverage neural networks as universal approximators of monotonic functions to build a parameterization of conditional cumulative distribution functions (CDFs).
no code implementations • NeurIPS 2016 • Yin Cheng Ng, Pawel Chilinski, Ricardo Silva
Factorial Hidden Markov Models (FHMMs) are powerful models for sequential data but they do not scale well with long sequences.