active_learning
adaptive
active_learning | adaptive | |
---|---|---|
1 | 11 | |
52 | 1,112 | |
- | 1.6% | |
1.8 | 6.2 | |
over 2 years ago | 8 days ago | |
Python | Python | |
MIT License | BSD 3-clause "New" or "Revised" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
active_learning
-
Active Learning at the ImageNet Scale
Code: https://github.com/zeyademam/active_learning
adaptive
-
I made a Python package to do adaptive learning of functions in parallel [P]
Imagine you have a drawing with lots of hills and valleys, and you want to understand the shape of the landscape. Instead of measuring the height at every single point, Adaptive helps you measure the height at the most important points. It focuses on areas where the hills and valleys change a lot, so you can understand the drawing with fewer measurements.
-
I made a Python package to do adaptive sampling of functions in parallel [OC]
Yes! Check it out at https://github.com/python-adaptive/adaptive/
Explore and star ⭐️ the repo on github.com/python-adaptive/adaptive, and check out the documentation at adaptive.readthedocs.io.
-
Introducing Markdown Code Runner: Automatically execute code blocks in your Markdown files! 🚀
Also, Quatro will require a YAML annotation at the top of the file that will always be visible, e.g., a notebook on GitHub: https://github.com/python-adaptive/adaptive/blob/main/docs/source/tutorial/tutorial.DataSaver.md
- Does Julia have something like pythons adaptive?
-
Graph plotting software for nasty function
Getting Python to calculate the equation for you shouldn't be a problem. The problem is that it may be having trouble figuring out which points to sample from. Using a uniformly spaced set of points won't necessarily result in the best looking curve, especially after interpolation. There is the adaptive package which does smart sampling of expensive functions. The idea is you give the function, and the adaptive library will learn the best x values to use and also return f(x).
What are some alternatives?
modAL - A modular active learning framework for Python
tensorflow - An Open Source Machine Learning Framework for Everyone
diffgram - The AI Datastore for Schemas, BLOBs, and Predictions. Use with your apps or integrate built-in Human Supervision, Data Workflow, and UI Catalog to get the most value out of your AI Data.
scikit-learn - scikit-learn: machine learning in Python
lightly - A python library for self-supervised learning on images.
Keras - Deep Learning for humans
gym - A toolkit for developing and comparing reinforcement learning algorithms.
Prophet - Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
xgboost - Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
PaddlePaddle - PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice (『飞桨』核心框架,深度学习&机器学习高性能单机、分布式训练和跨平台部署)
MindsDB - The platform for customizing AI from enterprise data
H2O - H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.