Highlights
- Pro
Block or Report
Block or report murphyk
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
probml/pyprobml Public
Python code for "Machine learning: a probabilistic perspective" (2nd edition)
1,413 contributions in the last year
Less
More
Contribution activity
February 2022
Created 23 commits in 4 repositories
Created an issue in janosh/awesome-normalizing-flows that received 2 comments
List stuff in reverse chronological order (newest to oldest)
Hi! This page is awesome (hence the name :) However it would be even more useful if you listed things (especially code) newest first, instead of ol…
2
comments
Opened 27 other issues in 5 repositories
probml/pyprobml
12
open
- implement Bayesian Online Changepoint Detection in JAX
- implement deep kalman filter in JSL
- add backwards sampling to kalman_smoother code
- implement blocked gibbs sampling for Bayesian inference in linear Gaussian SSM using JSL
- implement causal impact using JSL
- Make a JAX GAN demo in Colab
- make pedagogical JAX EBM demos
- update score matching JAX demo
- make some JAX normalizing flows demos
- implement hierarchical Gaussian filter
- 2d blind deconvolution with PGMs
- tackle JSL issues
lindermanlab/ssm-jax-refactor
4
open
2
closed
- typo in comment string for PoissonLDS default emission_weights
- efficiency: M step for poisson likelihood for LDS
- documentation: add dosctrings from ssm/distributions to https://ssm-jax-refactor.readthedocs.io/
- staleness: replace jax.experimental.optimizers with jax.optax
- installation: avoid specifying jax==0.2.21
- documentation: how can we extract the emission parameters from a model?