Differences

This shows you the differences between two versions of the page.

--- network_stuff:machine_learning:supervised_learning [2023/05/31 17:16] – jotasandoku
+++ network_stuff:machine_learning:supervised_learning [2023/11/02 14:38] (current) – external edit 127.0.0.1
@@ Line 3: / Line 3: @@
 In python, we use the method ''fit'' to **train a model**. Fit~train
   kmeans.fit(argument)
-  kmeans.predict (argument)    # ython predict() predicts the labels of the data values based on the trained model.
+  kmeans.predict (argument)    # Python predict() predicts the labels of the data values based on the trained model.
 \\
 REGRESSION\\
@@ Line 10: / Line 10: @@
 ----
-DECISON TRESS\\
+DECISON TREES:
+\\
   * k-nearest neighbors
-    * ~ "classification by proximity"
+    * ~ "classification by proximity" ; majority vote
     * after doing it with all points, it creates a "boundary" (ie classification)
-  * decision trees
+  * Decision trees
+    * decision by path to leaves ; measure of center
     * we ask question to narrow down areas (normally y/n Qs)
     * decision trees can surface relationships that were not evident for the human understanding.
-  * random forests(?)
+  * Random forests: decision trees tend to overfitting. A solution is 'random forest'. Is a collection of decision trees (often hundreds of them), each trained differently on the same data,

dokucama