Skip to main content

Machine Learning interface for High Energy Physics Phenomenology

Project description

PhenoAI is a machine learning interface for applications in High Energy Physics Phenomenology. It allows the user to use trained machine learning algorithms from the PhenoAI algorithm library (see link below) via a consistent interface. Trained algorithms can be stored in a folder with PhenoAI structure using the maker module of the package and shared, making it possible to communicate full-dimensional results so that one does not have to flee to models with lower dimensionality or to project out informative dimensions of the full problem.

Algorithm library

The current version of the package allows the user to use algorithms trained by scikit-learn and keras. These algorithms have to be created by the user, or have to be loaded from an external source like the algorithm library: http://hef.ru.nl/~bstienen/phenoai (work in progress).

Documentation

Documentation, a quick start guide and a range of examples can be found on the official PhenoAI website: http://hef.ru.nl/~bstienen/phenoai.

Citation

[coming soon]

To Do

  • Add support for ROOT trained algorithms

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

phenoai-0.1.3.tar.gz (51.2 kB view details)

Uploaded Source

File details

Details for the file phenoai-0.1.3.tar.gz.

File metadata

  • Download URL: phenoai-0.1.3.tar.gz
  • Upload date:
  • Size: 51.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.11.0 pkginfo/1.4.2 requests/2.19.1 setuptools/40.0.0 requests-toolbelt/0.8.0 tqdm/4.23.4 CPython/3.6.5

File hashes

Hashes for phenoai-0.1.3.tar.gz
Algorithm Hash digest
SHA256 3da322a53ded95ffbe80a5adee4ce4a537760f8de1967a5cc2a80eea90ad33d7
MD5 4aa215a50b4c589f2b6c0313b6a4e029
BLAKE2b-256 6f6fbd958c6f833a58a4a800f3917dfc3ca62f153098eaeedf72a6a0b0fd362e

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page