Official community-driven Azure Machine Learning examples, tested with GitHub Actions.
Обновлено 2024-11-20 16:48:44 +03:00
A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.
machine-learning
deep-learning
data-science
python
automated-machine-learning
natural-language-processing
hyperparameter-optimization
automl
jupyter-notebook
timeseries-forecasting
tuning
classification
finetuning
hyperparam
natural-language-generation
random-forest
regression
scikit-learn
tabular-data
Обновлено 2024-11-20 10:51:18 +03:00
12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
machine-learning
python
data-science
ml
scikit-learn
r
machine-learning-algorithms
machinelearning
education
scikit-learn-python
machinelearning-python
Обновлено 2024-11-11 23:02:40 +03:00
Python notebooks with ML and deep learning examples with Azure Machine Learning Python SDK | Microsoft
Обновлено 2024-11-04 20:20:56 +03:00
10 Weeks, 20 Lessons, Data Science for All!
Обновлено 2024-10-15 14:01:26 +03:00
Microsoft Azure Traces
Обновлено 2024-09-28 20:49:03 +03:00
Explore machine learning and data science with Codespaces
Обновлено 2024-08-12 16:11:43 +03:00
Notebooks and documentation for AI-for-Earth-managed datasets on Azure
Обновлено 2024-07-25 14:51:04 +03:00
Azure Data Explorer can provide valuable insights into your IoT workloads. In the following Hands-On Lab we look at thermostat IoT Devices that are in 3 different office buildings.
Обновлено 2024-04-30 01:41:27 +03:00
Best Practices, code samples, and documentation for Computer Vision.
microsoft
azure
machine-learning
python
deep-learning
data-science
computer-vision
kubernetes
artificial-intelligence
object-detection
tutorial
jupyter-notebook
convolutional-neural-networks
image-classification
image-processing
operationalization
similarity
Обновлено 2023-10-18 19:13:00 +03:00
Jupyter Notebooks on Azure for Genomics Data Analysis
Обновлено 2023-10-09 23:25:33 +03:00
Build sim from data for use in reinforcement learning and bonsai platform for machine teaching.
Обновлено 2023-09-07 19:12:44 +03:00
🌱 Join a community of developers at Microsoft Reactor and connect with people, skills, and technology to build your career or personal learning. We offer free livestreams, on-demand content, and hybrid/in-person events daily around the world. Access our projects and code here.
dotnet
azure
python
data-science
nodejs
ai
ml
mixed-reality
devops
iot
web
data
cloud
events
low-code
live-streaming
meetup
no-code
personal-de
Обновлено 2023-09-01 14:55:23 +03:00
Debugging, monitoring and visualization for Python Machine Learning and Data Science
machine-learning
python
deep-learning
data-science
ai
monitoring
reinforcement-learning
jupyter
jupyter-notebook
debugging
deeplearning
debug
machinelearning
explainable-ai
explainable-ml
saliency
debugging-tool
model-visualization
Обновлено 2023-08-30 10:47:36 +03:00
With AutoBrewML Framework the time it takes to get production-ready ML models with great ease and efficiency highly accelerates.
microsoft
machine-learning
data-science
anomaly-detection
nlp-machine-learning
sampling-strategies
text-analysis
text-classification
text-summarization
azure-automl
cleansing-data
datavisualization
responsible-ml
Обновлено 2023-08-03 09:43:02 +03:00
Azure Data Explorer advanced analytics library (functions, queries, etc.)
Обновлено 2023-07-24 10:20:42 +03:00
Azure AI Camp - 2 day workshop on Databricks and Azure ML
Обновлено 2023-07-23 07:44:56 +03:00
Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.
machine-learning
python
data-science
ner
synthetic-data
synthetic-data-generation
data-generation
ocr-recognition
synthetic-images
text-alignment
Обновлено 2023-07-20 18:03:32 +03:00
Normalized Trend Filtering for Biomedical Datasets
Обновлено 2023-07-07 01:07:14 +03:00
A processing engine for prio data
Обновлено 2023-07-06 23:08:33 +03:00
This project created to analyze, compare and identify whale tails from the Kaggle competition dataset, "Humpback Whale Identification Challenge". It is written in Python, and uses the Keras API with Tensorflow backend. The project implemented both a Siamese Network and a SoftMax classifier with center loss.
Обновлено 2023-06-12 22:29:42 +03:00
Quick useful examples of data science & ML & big data
Обновлено 2023-06-12 22:28:36 +03:00
MS MARCO(Microsoft Machine Reading Comprehension) is a large scale dataset focused on machine reading comprehension, question answering, and passage ranking. A variant of this task will be the part of TREC and AFIRM 2019. For Updates about TREC 2019 please follow This Repository Passage Reranking task Task Given a query q and a the 1000 most relevant passages P = p1, p2, p3,... p1000, as retrieved by BM25 a succeful system is expected to rerank the most relevant passage as high as possible. For this task not all 1000 relevant items have a human labeled relevant passage. Evaluation will be done using MRR
Обновлено 2023-06-12 21:21:58 +03:00
Test data for notebook exploration in VS Code
Обновлено 2023-06-12 21:19:08 +03:00
Course for Installing and Operating SQL Server Big Data Clusters on Red Hat OpenShift
Обновлено 2023-06-12 21:17:27 +03:00
Place for resources related to Data Exposed
Обновлено 2023-06-12 21:15:40 +03:00
Deep Metric Transfer for Label Propagation with Limited Annotated Data
Обновлено 2023-06-03 07:09:23 +03:00
Magic functions for using Jupyter Notebook with Azure Data Service
Обновлено 2023-03-28 19:45:37 +03:00
Sample notebooks for optimized training and inference of Hugging Face models on Azure Databricks
Обновлено 2023-03-28 19:41:14 +03:00
Cloud-Scale Data for Spring Developers Quick Start Guide
Обновлено 2022-11-29 01:22:11 +03:00