UMNN
Implementation of Unconstrained Monotonic Neural Network and the related experiments. These architectures are particularly useful for modelling monotonic transformations in normalizing flows.
Implementation of Unconstrained Monotonic Neural Network and the related experiments. These architectures are particularly useful for modelling monotonic transformations in normalizing flows. The project is written primarily in Python, distributed under the BSD 3-Clause "New" or "Revised" License license, first published in 2019. Key topics include: monotonic, neural-network, normalizing-flows.
No README available for this repository.
Contributors
Showing top 2 contributors by commit count.
Related Repositories
nemequ/portable-snippets
Collection of miscellaneous portable C snippets.
troglobit/libuev
Lightweight event loop library for Linux epoll() family APIs
massivefermion/birl
datetime handling for gleam
matlab-deep-learning/constrained-deep-learning
Constrained deep learning is an advanced approach to training deep neural networks by incorporating domain-specific constraints into the learning process.
atdt/monotonic
An implementation of time.monotonic() for Python 2 & Python 3
corsis/clock
High-resolution clock functions: monotonic, realtime, cputime.