kekeblom/DeepCGP
Deep convolutional gaussian processes.
This helps researchers and machine learning practitioners who work with image classification tasks. It takes image datasets like MNIST and CIFAR-10 as input and produces improved image classification accuracy by effectively detecting hierarchical combinations of local features. The primary users are those focused on advancing Bayesian machine learning techniques for computer vision.
No commits in the last 6 months.
Use this if you are exploring deep Gaussian processes for image classification and need a principled Bayesian framework for feature detection.
Not ideal if you need a readily deployable, production-ready image classification system or if you are not comfortable with advanced machine learning research concepts.
Stars
82
Forks
19
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Sep 04, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kekeblom/DeepCGP"
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.