|
| 1 | +--- |
| 2 | +title: Release notes 1.4.1 |
| 3 | +tags: [getting_started,release_notes] |
| 4 | +keywords: release notes, announcements, what's new, new features |
| 5 | +last_updated: May 7, 2017 |
| 6 | +summary: "Version 1.4.2 of DynaML, released May 7, 2017. Updates, improvements and new features." |
| 7 | +sidebar: mydoc_sidebar |
| 8 | +permalink: mydoc_release_notes_141.html |
| 9 | +folder: mydoc |
| 10 | +--- |
| 11 | + |
| 12 | +## Core API |
| 13 | + |
| 14 | +### Additions |
| 15 | + |
| 16 | + |
| 17 | +**Package** `dynaml.models.neuralnets` |
| 18 | + |
| 19 | + - Added `GenericAutoEncoder[LayerP, I]`, the class `AutoEncoder` is now **deprecated** |
| 20 | + - Added `GenericNeuralStack[P, I, T]` as a base class for Neural Stack API |
| 21 | + - Added `LazyNeuralStack[P, I]` where the layers are lazily spawned. |
| 22 | + |
| 23 | +**Package** `dynaml.kernels` |
| 24 | + |
| 25 | + - Added `ScaledKernel[I]` representing kernels of scaled Gaussian Processes. |
| 26 | + |
| 27 | +**Package** `dynaml.models.bayes` |
| 28 | + |
| 29 | + - Added `*` method to `GaussianProcessPrior[I, M]` which creates a scaled Gaussian Process prior using the newly minted `ScaledKernel[I]` class |
| 30 | + - Added Kronecker product GP priors with the `CoRegGPPrior[I, J, M]` class |
| 31 | + |
| 32 | +**Package** `dynaml.models.stp` |
| 33 | + |
| 34 | + - Added multi-output Students' T Regression model of [Conti & O' Hagan](http://www.sciencedirect.com/science/article/pii/S0378375809002559) in class `MVStudentsTModel` |
| 35 | + |
| 36 | +**Package** `dynaml.probability.distributions` |
| 37 | + |
| 38 | + - Added `HasErrorBars[T]` generic trait representing distributions which can generate confidence intervals around their mean value. |
| 39 | + |
| 40 | + |
| 41 | +### Improvements |
| 42 | + |
| 43 | + |
| 44 | +**Package** `dynaml.probability` |
| 45 | + |
| 46 | + - Fixed issue with creation of `MeasurableFunction` instances from `RandomVariable` instances |
| 47 | + |
| 48 | +**Package** `dynaml.probability.distributions` |
| 49 | + |
| 50 | + - Changed error bar calculations and sampling of Students T distributions (vector and matrix) and Matrix Normal distribution. |
| 51 | + |
| 52 | +**Package** `dynaml.models.gp` |
| 53 | + |
| 54 | + - Added _Kronecker_ structure speed up to `energy` (marginal likelihood) calculation of multi-output GP models |
| 55 | + |
| 56 | +**Package** `dynaml.kernels` |
| 57 | + - Improved implicit paramterization of Matern Covariance classes |
| 58 | + |
| 59 | + |
| 60 | +**General** |
| 61 | + |
| 62 | + - Updated breeze version to latest. |
| 63 | + - Updated Ammonite version to latest |
0 commit comments