usg-artificial-intelligence
There are 19 repositories under usg-artificial-intelligence topic.
nasa/delta
Deep Learning for Satellite Imagery
nasa/ML-airport-taxi-out
The ML-airport-taxi-out software is developed to provide a reference implementation to serve as a research example how to train and register Machine Learning (ML) models intended for four distinct use cases: 1) unimpeded AMA taxi out, 2) unimpeded ramp taxi out, 3) impeded AMA taxi out, and 4) impeded ramp taxi out. The software is designed to point to databases which are not provided as part of the software release and thus this software is only intended to serve as an example of best practices. The software is built in python and leverages open-source libraries kedro, scikitlearn, MLFlow, and others. The software provides examples how to build three distinct pipelines for data query and save, data engineering, and data science. These pipelines enable scalable, repeatable, and maintainable development of ML models.
nasa/pymdptoolbox
Markov Decision Process (MDP) Toolbox for Python
nasa/ML-airport-configuration
The ML-airport-configuration software is developed to provide a reference implementation to serve as a research example how to train and register Machine Learning (ML) models intended for predicting airport configuration as a time series. The software is designed to point to databases which are not provided as part of the software release and thus this software is only intended to serve as an example of best practices. The software is built in python and leverages open-source libraries kedro, scikitlearn, MLFlow, and others. The software provides examples how to build three distinct pipelines for data query and save, data engineering, and data science. These pipelines enable scalable, repeatable, and maintainable development of ML models.
nasa/concept-tagging-api
Contains code for the API that takes in text and predicts concepts & keywords from a list of standardized NASA keywords. API is for exposing models created with the repository `concept-tagging-training`.
nasa/concept-tagging-training
Contains code for training NLP models that takes in text and predicts concepts & keywords from a list of standardized NASA keywords. Code for the API that uses models trained by this repo is in `concept-tagging-api` repository.
CDCgov/NLPWorkbench
Natural Language processing for Pathology reports on cancer histology, laterality, side, and behavior.
nasa/Reinforcement-Learning-Benchmarking
Scripts for running several OpenAI Baselines algorithms on all MuJoCo or Roboschool gym environments to compare performance.
nasa/ML-airport-arrival-runway
The ML-airport-arrival-runway software is developed to provide a reference implementation to serve as a research example how to train and register Machine Learning (ML) models intended for predicting arrival runway assignments. The software is designed to point to databases which are not provided as part of the software release and thus this software is only intended to serve as an example of best practices. The software is built in python and leverages open-source libraries kedro, scikitlearn, MLFlow, and others. The software provides examples how to build three distinct pipelines for data query and save, data engineering, and data science. These pipelines enable scalable, repeatable, and maintainable development of ML models.
nasa/ML-airport-departure-runway
The ML-airport-departure-runway software is developed to provide a reference implementation to serve as a research example how to train and register Machine Learning (ML) models intended for predicting departure runway assignments. The software is designed to point to databases which are not provided as part of the software release and thus this software is only intended to serve as an example of best practices. The software is built in python and leverages open-source libraries kedro, scikitlearn, MLFlow, and others. The software provides examples how to build three distinct pipelines for data query and save, data engineering, and data science. These pipelines enable scalable, repeatable, and maintainable development of ML models.
cdcai/premier_analysis
A deep learning project predicting hyperinflammatory syndrome among COVID-19 patients using EHR data.
nasa/ML-airport-taxi-in
The ML-airport-taxi-in software is developed to provide a reference implementation to serve as a research example how to train and register Machine Learning (ML) models intended for four distinct use cases: 1) unimpeded AMA taxi in, 2) unimpeded ramp taxi in, 3) impeded AMA taxi in, and 4) impeded ramp taxi in. The software is designed to point to databases which are not provided as part of the software release and thus this software is only intended to serve as an example of best practices. The software is built in python and leverages open-source libraries kedro, scikitlearn, MLFlow, and others. The software provides examples how to build three distinct pipelines for data query and save, data engineering, and data science. These pipelines enable scalable, repeatable, and maintainable development of ML models.
CDCgov/legionella_pneumophila_genomics
This repository contains bioinformatics scripts and a Docker container to perform the in silico prediction of Legionella pneumophila serogroup from short read sequences using a supervised machine learning approach.
cdcai/NRC
Natural language generation for discrete data in EHRs
cdcai/R-tensorflow-projects
Random examples of Tensorflow in R
cdcai/autism_surveillance
Text classification algorithms for autism surveillance
cdcai/enriched-LSTMs
Classifying multimodal health data with LSTMs
cdcai/injury-autocoding
An ensemble of BERTs for classifying injury narratives