Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Probabilistic reasoning and statistical analysis in TensorFlow
| Date | Stars |
|---|---|
| 2026-07-24 | 4421 |
| 2026-07-25 | 4421 |
| 2026-07-28 | 4421 |
| 2026-07-30 | 4421 |
| 2026-08-08 | 4423 |
| 2026-08-16 | 4425 |
| 2026-08-18 | 4426 |
| 2026-08-20 | 4427 |
| 2026-08-21 | 4428 |
| 2026-08-22 | 4427 |
| 2026-08-23 | 4427 |
| 2026-08-27 | 4428 |
| 2026-08-28 | 4429 |
| 2026-08-29 | 4430 |
| 2026-08-30 | 4431 |
| 2026-09-01 | 4430 |
| 2026-09-02 | 4430 |
| 2026-09-03 | 4431 |
| 2026-09-04 | 4432 |
| 2026-09-07 | 4432 |
| 2026-09-10 | 4433 |
| 2026-09-14 | 4432 |
| 2026-09-16 | 4431 |
| 2026-09-19 | 4433 |
| 2026-09-20 | 4433 |
Today
— stars today
This week
— stars this week
This month
+5 stars this month
Momentum
0.0
growth rate 0.00%/day
# TensorFlow Probability
TensorFlow Probability is a library for probabilistic reasoning and statistical
analysis in TensorFlow. As part of the TensorFlow ecosystem, TensorFlow
Probability provides integration of probabilistic methods with deep networks,
gradient-based inference via automatic differentiation, and scalability to
large datasets and models via hardware acceleration (e.g., GPUs) and distributed
computation.
__TFP also works as "Tensor-friendly Probability" in pure JAX!__:
`from tensorflow_probability.substrates import jax as tfp` --
Learn more [here](https://www.tensorflow.org/probability/examples/TensorFlow_Probability_on_JAX).
Our probabilistic machine learning tools are structured as follows.
__Layer 0: TensorFlow.__ Numerical operations. In particular, the LinearOperator
class enables matrix-free implementations that can exploit special structure
(diagonal, low-rank, etc.) for efficient computation. It is built and maintained
by the TensorFlow Probability team and is now part of
[`tf.linalg`](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/python/ops/linalg)
in core TF.
__Layer 1: Statistical Building Blocks__
* Distributions ([`tfp.distributions`](https://github.com/tensorflow/probability/tree/main/tensorflow_probability/python/distributions)):
A large collection of probability
distributions and related statistics with batch and
[broadcasting](https://docs.scipy.org/doc/numpy/user/basics.broadcasting.html)
semantics. See the
[Distributions Tutorial](https://github.com/tensorflow/probability/blob/main/tensorflow_probability/examples/jupyter_notebooks/TensorFlow_Distributions_Tutorial.ipynb).
* Bijectors ([`tfp.bijectors`](https://github.com/tensorflow/probability/tree/main/tensorflow_probability/python/bijectors)):
Reversible and composable transformations of random variables. Bijectors
provide a rich class of transformed distributions, from classical examples
like the
[log-normal distribution](https://en.wikipedia.org/wiki/Log-normal_distribution)
to sophisticated deep learning models such as
[masked autoregressive flows](https://arxiv.org/abs/1705.07057).
__Layer 2: Model Building__
* Joint Distributions (e.g., [`tfp.distributions.JointDistributionSequential`](https://github.com/tensorflow/probability/tree/main/tensorflow_probability/python/distributions/joint_distribution_sequential.py)):
Joint distributions over one or more possibly-interdependent distributions.
For an introduction to modeling with TFP's `JointDistribution`s, check out
[this colab](https://github.com/tensorflow/probability/blob/main/tensorflow_probability/examples/jupyter_notebooks/Modeling_with_JointDistribution.ipynb)
* Probabilistic Layers ([`tfp.layers`](https://github.com/tensorflow/probability/tree/main/tensorflow_probability/python/layers)):
Neural network layers with uncertainty over the functions they represent,
extending TensorFlow Layers.
__Layer 3: Probabilistic Inference__
* Markov chain Monte Carlo ([`tfp.mcmc`](https://github.com/tensorflow/probability/tree/main/tensorflow_probability/python/mcmc)):
Algorithms for approximating integrals via sampling. Includes
[Hamiltonian Monte Carlo](https://en.wikipedia.org/wiki/Hamiltonian_Monte_Carlo),
random-walk Metropolis-Hastings, and the ability to build custom transition
kernels.
* Variational Inference ([`tfp.vi`](https://github.com/tensorflow/probability/tree/main/tensorflow_probability/python/vi)):
Algorithms for approximating integrals via optimization.
* Optimizers ([`tfp.optimizer`](https://github.com/tensorflow/probability/tree/main/tensorflow_probability/python/optimizer)):
Stochastic optimization methods, extending TensorFlow Optimizers. Includes
[Stochastic Gradient Langevin Dynamics](http://www.icml-2011.org/papers/398_icmlpaper.pdf).
* Monte Carlo ([`tfp.monte_carlo`](https://github.com/tensorflow/probability/blob/main/tensorflow_probability/python/monte_carlo)):
Tools for computing Monte CExcerpt of 11,920 characters
Read on GitHub
Matthew Johnson · Google · United States
1.9k
Peter Hawkins · Google
1.4k
612
464
461
394
Alexey Radul
376
Roy Frostig · @google-deepmind
322
313
Jacob Burnim · @google · United States
299
286
250
Jake Vanderplas · Google
225
224
223
TensorFlower Gardener
222
Stephan Hoyer · Periodic Labs · United States
129
Colin Carroll
121
111
James Bradbury · Google
103
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:5b665da0ca8ba0ff, topic:deep-learning, topic:tensorflow, readme:automatic differentiation