Releases: modern-fortran/neural-fortran
Releases · modern-fortran/neural-fortran
neural-fortran-0.17.0
neural-fortran-0.16.1
What's Changed
- Addidtion of Findneural-fortran.cmake by @jvdp1 in #178
- Replacement of a matmul + use of merge by @jvdp1 in #181
Full Changelog: v0.16.0...v0.16.1
neural-fortran-0.16.0
What's Changed
- More conv2d tests by @milancurcic in #174
- Add instructions using Conda by @certik in #172
- Addition of the Loss derived type and of the MSE loss function by @jvdp1 in #175
New Contributors
Full Changelog: v0.15.1...v0.16.0
neural-fortran-0.15.1
What's Changed
- safegaurd Box-Muller normal random number generation against u=0.0 by @dacarnazzola in #158
New Contributors
- @dacarnazzola made their first contribution in #158
Full Changelog: v0.15.0...v0.15.1
neural-fortran-0.15.0
What's Changed
- Adagrad Optimizer Implementation by @Spnetic-5 in #154
Full Changelog: v0.14.0...v0.15.0
neural-fortran-0.14.0
What's Changed
- Added Adam optimizer implementation by @Spnetic-5 in #150
Full Changelog: v0.13.0...v0.14.0
neural-fortran-0.13.0
What's Changed
- Contributing guide by @milancurcic in #109
- GSoC Optimizers: Example program to fit a quadratic function by @Spnetic-5 in #134
- Update contributors and acknowledgment by @milancurcic in #138
- Add missing update for
conv2d_layer
by @milancurcic in #141 - Example program that shows how to access internal layer parameters by @milancurcic in #140
- add CELU activation function by @pablomazo in #143
- Added RMSProp Optimizer subroutine by @Spnetic-5 in #144
- SGD optimizer stub by @milancurcic in #139
- Connect
flatten
,conv2d
, andmaxpool2d
layers in backward pass by @milancurcic in #142 - Added Momentum and Nesterov modifications by @Spnetic-5 in #148
New Contributors
- @pablomazo made their first contribution in #143
Full Changelog: v0.12.0...v0.13.0
neural-fortran-0.12.0
What's Changed
- Added Leaky ReLU activation function (1D & 3D) by @Spnetic-5 in #123
- Class-based activation functions by @ggoyman in #126
New Contributors
- @Spnetic-5 made their first contribution in #123
- @ggoyman made their first contribution in #126
Full Changelog: v0.11.0...v0.12.0
neural-fortran-0.11.0
What's Changed
- Add missing edit descriptor by @milancurcic in #113
- Small workaround to make Intel compiler happy by @milancurcic in #117
- Introduce optimizer_base_type in support of different optimizers by @milancurcic in #116
- Insert a flatten layer if a dense layer follows a layer by @milancurcic in #118
- Add linear activation function by @milancurcic in #119
- Update contributors by @milancurcic in #120
Full Changelog: v0.10.0...v0.11.0
neural-fortran-0.10.0
This release introduces get_num_params
, get_params
, and set_params
methods to network
and layer
derived types, and allow you to more easily get and set network hyperparameters from custom Fortran code or other libraries. See the example to learn how it works.
Thanks to Christopher Zapart @jvo203 for this feature contribution.
What's Changed
- Fix CMake build by @milancurcic in #110
- Get set network parameters by @milancurcic in #111
Full Changelog: v0.9.0...v0.10.0