========================== GFDL 0.1.0 Release Notes ========================== .. contents:: Gradient free deep learning (GFDL) 0.1.0 is the culmination of 6 months of hard work. This first release contains three new estimators. Our development attention will now shift to bug-fix releases on the 0.1.x branch, and on adding new features on the main branch. This release requires Python 3.12-3.14. ************************** Highlights of this release ************************** * The new :class:`~gfdl.model.GFDLClassifier` is an estimator offering single and multi-layer random vector functional link (RVFL) and extreme learning machine (ELM) gradient-free neural networks. A regression equivalent, :class:`~gfdl.model.GFDLRegressor` has also been added. * The new :class:`~gfdl.model.EnsembleGFDLClassifier` offers a connected ensemble of estimators for multi-layer RVFLs that contribute to model output via soft or hard voting. ************ New features ************ ``gfdl.model`` improvements ============================ * Three new estimators that include single and multi layer extreme learning machines (ELMs) and random vector functional link (RVFL) networks: :class:`~gfdl.model.GFDLClassifier`, :class:`~gfdl.model.GFDLRegressor`, and :class:`~gfdl.model.EnsembleGFDLClassifier`. ******* Authors ******* * Name (commits) * Navamita Ray (138) * Tyler Reddy (149) + * Emma Viani (66) + A total of 3 people contributed to this release. People with a "+" by their names contributed a patch for the first time. This list of names is automatically generated, and may not be fully complete. ************************ Issues closed for 0.1.0 ************************ * `#11 `__: MAINT, BLD, DOC: project/estimator renaming * `#12 `__: BUG, ENH: Discrepancy between GrafoRVFL and RVFLRegressor for... * `#20 `__: DOC: landing page estimator list * `#21 `__: DOC: landing page example -- fix the seed * `#22 `__: DOC: ``range`` description improvement * `#23 `__: DOC: activations module docstring * `#24 `__: DOC: identity activation function return value description * `#25 `__: DOC: ``coeff_`` estimator attribution clarification * `#26 `__: DOC, CI: lint weights.py with ``numpydoc`` in the CI * `#27 `__: DOC: missing space in hidden_layer_sizes parameter * `#28 `__: DOC: several weights function have unused kwargs * `#29 `__: DOC: remove justification(s) for weight function abstractions? * `#30 `__: DOC: ChatGPT ref in docs * `#31 `__: DOC: He normal distribution return doc * `#34 `__: DOC, MAINT: conf.py ``GITHUB_REF`` likely not correct * `#38 `__: MAINT: CPython (and maybe other dep) runtime version checks * `#43 `__: DOC, MAINT: adding repo source URL to pyproject.toml ************************ Pull requests for 0.1.0 ************************ * `#2 `__: CI, BLD: support wheel builds, test in CI * `#3 `__: DOC: start adding numpydoc docstrings * `#5 `__: MAINT, CI: trove classifiers for PyPI; Windows testing * `#6 `__: MAINT: remove scripts from lib project * `#7 `__: DOC: README updates * `#8 `__: DOC: add BSD 3-clause license * `#9 `__: WIP, MAINT: remove dependence on graforvfl * `#10 `__: MAINT: module top cleanups * `#14 `__: CI, TST : Increase tolerance for Grafo checks. * `#15 `__: MNT: renaming RVFL to GFDL for consistency in repo * `#16 `__: CI: test wheels on Windows * `#17 `__: DOC, MAINT: tools script for release notes lists * `#18 `__: DOC, MAINT: tools script for author list * `#36 `__: MAINT, REL: set version to ``0.1.0.dev0`` * `#39 `__: DOC: document the process for releasing * `#40 `__: ENH: control rtol for regressor * `#41 `__: CI, DOC: lint ``weights.py`` in CI * `#42 `__: DOC: landing page improvements * `#44 `__: ENH, TST: Add rtol to classifier and a test. * `#45 `__: ENH, TST: Add rtol for ensemble estimators and a test. * `#46 `__: DOC, MAINT: repo source to pyproject.toml * `#48 `__: DOC: Update branch name for source linking * `#49 `__: DOC: Use default rng in landing page example * `#50 `__: DOC: Remove plural * `#51 `__: CI: run on maintenance branches as well * `#52 `__: DOC: Addresses multiple doc related issues * `#54 `__: MAINT: runtime min version enforcement