Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
1bbbb97
commit 90fcedc
Showing
2 changed files
with
26 additions
and
20 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,35 +1,41 @@ | ||
# CMT | ||
|
||
## 0.6.0 | ||
|
||
- Added limited MATLAB interface | ||
- Improved Python 3 compatibility | ||
- Bug fixes | ||
|
||
## 0.5.0 | ||
|
||
- Regularizers are now more flexible. | ||
- Several bug fixes and stability improvements. | ||
- Added binomial distribution. | ||
- Added StackedAffineTransform. | ||
- Regularizers are now more flexible | ||
- Several bug fixes and stability improvements | ||
- Added binomial distribution | ||
- Added StackedAffineTransform | ||
|
||
## 0.4.1 | ||
|
||
- Added multinomial logistic regression (MLR). | ||
- Added function for sampling images conditioned on component labels. | ||
- Extended MCGSM by additional parameters. | ||
- Added multinomial logistic regression (MLR) | ||
- Added function for sampling images conditioned on component labels | ||
- Extended MCGSM by additional parameters | ||
|
||
## 0.4.0 | ||
|
||
- Added spike-triggered mixture model (STM). | ||
- Added simple univariate distributions such as Bernoulli and Poisson. | ||
- Added generalized linear model (GLM) and fully-visible belief network (FVBN). | ||
- Added mixture of Gaussian scale mixture (MoGSM). | ||
- Added *PatchMCGSM*. | ||
- Extended MCGSM by linear features and means. | ||
- Made implementation of new conditional models easier by introducing interface *Trainable*. | ||
- Most methods of *MCGSM* can now cope with zero-dimensional inputs. | ||
- Added spike-triggered mixture model (STM) | ||
- Added simple univariate distributions such as Bernoulli and Poisson | ||
- Added generalized linear model (GLM) and fully-visible belief network (FVBN) | ||
- Added mixture of Gaussian scale mixture (MoGSM) | ||
- Added *PatchMCGSM* | ||
- Extended MCGSM by linear features and means | ||
- Made implementation of new conditional models easier by introducing interface *Trainable* | ||
- Most methods of *MCGSM* can now cope with zero-dimensional inputs | ||
|
||
## 0.3.0 | ||
|
||
- Implemented *early stopping* based on validation error. | ||
- Implemented *early stopping* based on validation error | ||
|
||
## 0.2.0 | ||
|
||
- Implemented mixture of conditional Boltzmann machines (MCBM). | ||
- Implemented *PatchMCBM*. | ||
- Extended tools for generating data from images and videos. | ||
- Implemented mixture of conditional Boltzmann machines (MCBM) | ||
- Implemented *PatchMCBM* | ||
- Extended tools for generating data from images and videos |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,2 +1,2 @@ | ||
__all__ = ["models", "transforms", "tools", "utils", "nonlinear"] | ||
__version__ = "1.5.1a" | ||
__version__ = "0.6.0" |