-
```
The alpha values and the beta prior used for estimating the LDA topic model
should be configurable. So far, the default values are always used (1.0 and
0.01 respectively).
Solution:
Mallet take…
-
Claudio Bustos' [distribution](http://github.com/clbustos/distribution) gem supplies the probability distributions for SciRuby.
Some of these have already been implemented (e.g., normal, chisquare, h…
-
Did you ever extend this package to include HDP priors for Gaussian Mixtures for the emission probabilities? I am trying to locate the acceptable probabilities for emission distributions, but can only…
-
Get help from Ben on setting up the include-what-you-use tool, then listen to it.
-
[PackageEvaluator.jl](https://github.com/IainNZ/PackageEvaluator.jl) is a script that runs nightly. It attempts to load all Julia packages and run their tests (if available) on both the stable version…
-
- [x] Outline terminology
- [x] Outline parameters
- [x] Define parameters
- [x] Outline flow
- [x] Research Bayes
- [x] Find prior distributions
- [x] Learning curve
- [x] Forgetting curve
- …
-
Two issues actually:
on pymc 2.3 under python 2.7, running a simple model based on Uniform I get results outside of the [lower-upper] interval and accordingly, the fit() method returns a RuntimeError…
-
[PackageEvaluator.jl](https://github.com/IainNZ/PackageEvaluator.jl) is a script that runs nightly. It attempts to load all Julia packages and run their tests (if available) on both the stable version…
-
Dirichlet distribution has been used extensively in statistics, as the conjugate prior for multinomial. And it can be treated as a generalization of beta distribution to multi variables.
Why not add …
-
[PackageEvaluator.jl](https://github.com/IainNZ/PackageEvaluator.jl) is a script that runs nightly. It attempts to load all Julia packages and run their tests (if available) on both the stable version…