Added resources and updated readme for BetaML

sylvaticus · Sep 10, 2020 · da5ba66 · da5ba66
1 parent f9113cd
commit da5ba66
Show file tree

Hide file tree

Showing 8 changed files with 11 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -14,7 +14,14 @@ _Disclaimer: The following notes are a mesh of my own notes, selected transcript
 <!--(PDF versions <del>may be </del> are <del>slightly</del> outdated)-->
 (PDF versions may be slightly outdated)
 
-For an implementation of the algorithms _in Julia_, see the companion repository "Beta Machine Learning Toolkit" [on GitHub](https://github.com/sylvaticus/Bmlt.jl ) or in [myBinder](https://mybinder.org/v2/gh/sylvaticus/Bmlt.jl/master) to run the code online by yourself (and if you are looking for an introductory book on Julia, have a look on [my one](https://www.julia-book.com/)).
+--------------------------------------------------------------------------------
+For an implementation of the algorithms _in Julia_ (a relatively recent language incorporating the best of R, Python and Matlab features with the efficiency of compiled languages like C or Fortran), see the companion repository "Beta Machine Learning Toolkit" [on GitHub](https://github.com/sylvaticus/BetaML.jl ) or in [myBinder](https://mybinder.org/v2/gh/sylvaticus/BetaML.jl/master) to run the code online by yourself (and if you are looking for an introductory book on Julia, have a look on [my one](https://www.julia-book.com/)).
+BetaML currently implements:
+- Linear, average and kernel Perceptron (units 1 and 2)
+- Feed-forward Neural Networks (unit 3)
+- Clustering (k-means, k-medoids and EM algorithm), recommandation system based on EM (unit 4)
+- Decision Trees / Random Forest (mentioned on unit 2)
+--------------------------------------------------------------------------------
 
 [PDF all in one document](MITx_6.86x_notes.md.pdf)
 

diff --git a/...sifiers and Generalizations/Unit 01 - Linear Classifiers and Generalizations.md b/...sifiers and Generalizations/Unit 01 - Linear Classifiers and Generalizations.md
@@ -335,6 +335,9 @@ The update function $\theta = \theta + x^i*y^i$ becomes then $\array{\theta\\\th
 So now we have a general learning algorithm.
 The simplest one, but it can be generalized to be quite powerful and therefore, hence it is a useful algorithm to understand.
 
+For example, we saw here a binary classification, but it can be easily be extended to a multiclass classification employing a "one vs all" strategy, as explained in [this SO answer](https://stats.stackexchange.com/a/87585/263905) or on [wikipedia](http://en.wikipedia.org/wiki/Multiclass_classification).
+
+
 _Code implementation: functions `perceptron_single_step_update()`, `perceptron()`, `average_perceptron()`, `pegasos_single_step_update()` and `pegasos()` in project1._
 
 

diff --git a/Unit 03 - Neural networks/Related resources/relu_activation_advantages_glorot11a.pdf b/Unit 03 - Neural networks/Related resources/relu_activation_advantages_glorot11a.pdf
diff --git a/Unit 04 - Unsupervised Learning/Related resources/1209.0521.pdf b/Unit 04 - Unsupervised Learning/Related resources/1209.0521.pdf
diff --git a/Unit 04 - Unsupervised Learning/Related resources/EM_GenerativeBinomialMixture.pdf b/Unit 04 - Unsupervised Learning/Related resources/EM_GenerativeBinomialMixture.pdf
diff --git a/...pervised Learning/Related resources/Imputation_through_finite_Gaussian_mixture_models.pdf b/...pervised Learning/Related resources/Imputation_through_finite_Gaussian_mixture_models.pdf
diff --git a/Unit 04 - Unsupervised Learning/Related resources/mixture_models.pdf b/Unit 04 - Unsupervised Learning/Related resources/mixture_models.pdf
diff --git a/Unit 05 - Reinforcement Learning/Related resources/AlphaGo Paper - nature24270.pdf b/Unit 05 - Reinforcement Learning/Related resources/AlphaGo Paper - nature24270.pdf