Skip to main content

High-Performance implementation of an Extreme Learning Machine

Project description

High Performance ELM
--------

Extreme Learning Machine (ELM) with model selection and regularizations.

In-memory ELM works, check hpelm/tests folder.
MAGMA acceleration works, check hpelm/acc/setup_gpu.py.


Example usage::

>>> from hpelm import ELM
>>> elm = ELM(X.shape[1], T.shape[1])
>>> elm.add_neurons(20, "sigm")
>>> elm.add_neurons(10, "rbf_l2")
>>> elm.train(X, T, "LOO")
>>> Y = elm.predict(X)

If you use the toolbox, cite our paper that will be published in IEEE Access.

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

hpelm-0.6.6.tar.gz (20.2 kB view details)

Uploaded Source

File details

Details for the file hpelm-0.6.6.tar.gz.

File metadata

  • Download URL: hpelm-0.6.6.tar.gz
  • Upload date:
  • Size: 20.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No

File hashes

Hashes for hpelm-0.6.6.tar.gz
Algorithm Hash digest
SHA256 555921340b7f4a7266f1f1bde8a5333fad0b0dd0e8a96c00a62ad523d42858fc
MD5 df91f4ac0bb249d0879916c45ccc6a8b
BLAKE2b-256 8a974f9bc8c749551d7ae2a1855656632a20bbbca55a8c114f680f78e73e6397

See more details on using hashes here.

Supported by

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