Commit e468a8b2 authored by Olivier Michel's avatar Olivier Michel 💬
Browse files

Update notebooks/8_Clustering/N1_Kmeans_basic.ipynb,...

Update notebooks/8_Clustering/N1_Kmeans_basic.ipynb, notebooks/8_Clustering/N2_KMeans_iris_data_example.ipynb, notebooks/8_Clustering/N3_Kernel_Kmeans_example.ipynb, notebooks/8_Clustering/N4_EM_basic.ipynb, notebooks/8_Clustering/N5_EM_iris_data_example.ipynb files
parent 8cb65c9f
......@@ -54,11 +54,11 @@
```
%% Cell type:markdown id: tags:
### Exercize
- Identify the arrays above wrt to the charateristics of the GMM introduced in th electure
- Identify the arrays above wrt to the charateristics of the GMM introduced in the lecture
- Explain why different means are initialized, whereas same variances may be used
- Comment the line codes below, briefly
%% Cell type:code id: tags:
......@@ -90,11 +90,12 @@
```
%% Cell type:markdown id: tags:
### Exercize
Below, the plot diplays the 2 Gaussian pdfs involved in the mixture; the mixture distribution to that plot.
- What is the array that informs about the labels that should be assigned to each observation? Print an example.
- Below, the plot diplays the 2 Gaussian pdfs involved in the mixture; add the mixture distribution to that plot.
%% Cell type:code id: tags:
``` python
Xt=np.linspace(-2,8,1000)
......@@ -196,6 +197,13 @@
%% Cell type:markdown id: tags:
### Exercize
- Compare and interpret Kmeans wrt EM;
- Interpret the reposability functions resp0 and resp1.
- Interpret the responsability functions resp0 and resp1.
- Why is EM sometimes interpreted as a "soft-Kmeans" algorithm? What would be the responsability curves for Kmeans?
%% Cell type:code id: tags:
``` python
```
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment