Skip to content

Releases: tonegas/nnodely

v1.5.5.dev2

v1.5.5.dev2 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 13 May 08:50
5fb68a6

What's Changed

Full Changelog: v1.5.2...v1.5.5.dev2

v1.5.5.dev1

v1.5.5.dev1 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 16 Apr 09:30

What's Changed

Full Changelog: v1.5.2...v1.5.5.dev1

v1.5.4

Choose a tag to compare

@github-actions github-actions released this 27 Feb 18:37
9cb4750
New nnodely version

In this new version of nnodely:

README completely revised that evidence, documentation, case-studies and applications
Extensively expanded documentation
Partial integration of neuralODE
Minor other fix

v1.5.2

Choose a tag to compare

@github-actions github-actions released this 09 Dec 21:48
ca8d7ef

This new version 1.5.2 of nnodely, featuring several updates:

  1. Fixes many bugs
  2. Improved the recurrent plot in matplotlib

v1.5.1

Choose a tag to compare

@github-actions github-actions released this 24 Jul 21:18
865c195

This new version 1.5.1 of nnodely, featuring several updates:

  1. Improved clarity of documentation and examples.
  2. Support for managing multi-dataset features is now available.
  3. DataFrames can now be used to create datasets.
  4. Datasets can now be resampled.
  5. Random data training has been fixed for both classic and recurrent training.
  6. The State variable has been removed.
  7. It is now possible to add or remove a connection or a closed loop.
  8. Partial models can now be exported.
  9. The trainModel function and the resultAnalysis have been separated.
  10. A new function, trainAndAnalyse, is now available.
  11. The report now works across all network types.
  12. The training function code has been reorganized.
  13. New plotting function for network structure

v1.3.1

Choose a tag to compare

@github-actions github-actions released this 12 Mar 12:36
933c815

Here's the new version of nnodely!
In this new version, you can:

  1. derive and integrate streams;
  2. create a time or sample window on the stream;
  3. create the new equation learner layer.
  4. call easly the parametric function using a simplified inputs that improve the flexibility and reliability.

In addition, countless bugs have been fixed and the warning and error system has been hardened.
Moreover the domumentation is improved and it has been included in the tests.

v1.0.0

Choose a tag to compare

@github-actions github-actions released this 30 Jan 16:13
aecf70f

It’s time to build—nnodely 1.0.0 is officially here!

The main functionalities of this first version are:

  1. Build your forward neural models using the basic building blocks: Activation Trigonometric and Aritmetic functions, Linear and Fir layers, Fuzzy layers and Local Models, and custom Parametric Function.
  2. Build your neural controllers using Connect and CloseLoop operations.
  3. Load multiple datasets from different files.
  4. Train from a network's piece to the whole network, including loops and connections.
  5. Export your controller or your estimator in stand-alone Pytorch or Onnx.

v0.25.0

v0.25.0 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 11 Dec 17:29
8e8382e
Merge pull request #35 from tonegas/features/1-setup-the-documentation

Modified the version

v0.24.0

v0.24.0 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 06 Dec 20:32
0659f1b
Merge pull request #19 from tonegas/fixes/1-test

New version for test check push

v0.23.0

v0.23.0 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 06 Dec 19:26
0d31a96
Merge pull request #18 from tonegas/fixes/1-test

New version after clean the repository files