zakeria/uGMM
A novel neural architecture that embeds probabilistic reasoning directly into the computational units of deep networks.
This project offers a novel way for deep learning researchers to build neural networks where each 'neuron' can understand and represent a range of possibilities, not just a single value. It takes in standard numerical data, like image pixels or sensor readings, and produces predictions that inherently include a measure of uncertainty. This allows researchers to explore new model architectures that combine the strengths of deep learning with probabilistic reasoning.
Use this if you are a deep learning researcher experimenting with new neural network architectures and want to integrate probabilistic reasoning directly into your models.
Not ideal if you are a practitioner looking for an off-the-shelf solution for common machine learning tasks without needing to delve into novel architecture design.
Stars
8
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jan 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zakeria/uGMM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sbi-dev/sbi
sbi is a Python package for simulation-based inference, designed to meet the needs of both...
SMTorg/smt
Surrogate Modeling Toolbox
reservoirpy/reservoirpy
A simple and flexible code for Reservoir Computing architectures like Echo State Networks
GPflow/GPflow
Gaussian processes in TensorFlow
thousandbrainsproject/tbp.monty
Monty is a sensorimotor learning framework based on the thousand brains theory of the neocortex.