Quiz 0.2 doen and changed 0004 vid (for better audio)

Unless problems arise, shis SHOULD be the complete version of the course

lessonsSources/00_-_INTRO_-_Introduction_julia_ml/0001_-_Course_presentation.md

@@ -11,7 +11,7 @@ In particular, by attending this course you will receive :
 3. An overview of modern tools for scientific collaboration and software quality, such as version control systems and best practices to obtain replicable results.
 4. An introduction to machine learning approaches: scopes, terminology, typologies, workflow organisation
 5. An in-deep introduction to some specific machine learning algorithms for classification and regression (perceptron, neural networks, random forests..)
-6. Experience is employing Machine Learning workflows to specific cases on multiple domains
+6. Experience in employing Machine Learning workflows to specific cases on multiple domains
 
 ## How to attend the course
 

lessonsSources/00_-_INTRO_-_Introduction_julia_ml/0002_-_Program.md

@@ -12,7 +12,7 @@ Take-home tip: in your projects, implement the introduction and the conclusions
 
 The slides used in the videos below are available [here](https://github.com/sylvaticus/SPMLJ/blob/main/lessonsSources/00_-_INTRO_-_Introduction_julia_ml/assets/00_KOMEETING.pdf).
 
-- [Course introduction](https://www.youtube.com/watch?v=ozdfSX2uk2E&list=PLDIpPSqVuMmLGUNGMXL2eO2pqKlzdPfxa&index=1) (6:03)
+- [Course introduction](https://www.youtube.com/watch?v=82IbUHUgzLo&list=PLDIpPSqVuMmLGUNGMXL2eO2pqKlzdPfxa&index=1) (6:03)
 - [Julia overview](https://www.youtube.com/watch?v=uW8iyTjSaJk&list=PLDIpPSqVuMmLGUNGMXL2eO2pqKlzdPfxa&index=2) (36:25)
 - Hands on (42:09)
   - [Part A](https://www.youtube.com/watch?v=kT9Vm8Ov6qo&list=PLDIpPSqVuMmLGUNGMXL2eO2pqKlzdPfxa&index=3) (20:15)
@@ -91,4 +91,4 @@ The slides used in the videos below are available [here](https://github.com/sylv
   - [Part A - Binary classification](https://www.youtube.com/watch?v=IFVz0jsy5AQ&list=PLDIpPSqVuMmIvTA3w7ATUKHzq82uey8pP&index=7) (15:54)
   - [Part B - Multinomial classification](https://www.youtube.com/watch?v=fqROq7B6nyY&list=PLDIpPSqVuMmIvTA3w7ATUKHzq82uey8pP&index=8) (15:1)
   - [Part C - Regression](https://www.youtube.com/watch?v=jO-mfgzo7VY&list=PLDIpPSqVuMmIvTA3w7ATUKHzq82uey8pP&index=9) (6:3)
-  - [Part D - Convolutional neural network](https://www.youtube.com/watch?v=mSUdLu9HAd4&list=PLDIpPSqVuMmIvTA3w7ATUKHzq82uey8pP&index=10) (13:19)
+  - [Part D - Convolutional neural network](https://www.youtube.com/watch?v=mSUdLu9HAd4&list=PLDIpPSqVuMmIvTA3w7ATUKHzq82uey8pP&index=10) (13:19)

lessonsSources/00_-_INTRO_-_Introduction_julia_ml/0004q_-_QUIZ_0.2.md

@@ -12,7 +12,7 @@ using QuizQuestions
 ```
 
 --------------------------------------------------------------------------------
-### Q1: What is ML?
+### Q1: What is Machine Learning?
 
 Which could be considered examples of Machine Learning ?
 
@@ -43,3 +43,36 @@ The correct answer are:
 </details>
 ```
 
+--------------------------------------------------------------------------------
+### Q2: Kind of mchine Learning tasks
+
+Which of the following statements are correct ?
+
+```@example q0002
+
+choices = [ # hide
+  "In unsupervised (machine) learning the objective is to learn the relation between some inputs and some outputs from a sequence of pairs (inputs, outputs) provided to the algorithm", # hide
+  "In supervised machine learning tasks the objective is to lean the relation between the provided features (inputs) and the provided labels (outputs)", # hide
+  "In reinforcment learning tasks, the algorithm must find the best actions for a certain agent to perform given the different states of the words, the rewards that the agent is given at each possible state and the probabilities to reach the various states given the departing state and the available actions", # hide
+  "None of the (other) sentences is correct", # hide
+  ]  # hide
+answers = [4]  # hide
+multiq(choices, answers;keep_order=true)  # hide
+```
+
+```@raw html
+<details><summary>RESOLUTION</summary>
+```
+All sentences are wrong. Unsupervise machine learning, by definition, includes algorithms for which we do not provide exemples of a "correct" output for the different inputs. We try instead to find a pattern, a structure in the data itself.
+
+Outputs are provided in supervised tasks. However the sentence reported is wrong, because we are not interested much in the relationship between the _provided_ inputs and outputs, but in finding a generic relationship between the inputs and the outputs for the population from which the data arise.
+
+Fianlly, also the sentence on reinforcement learning is wrong, because in reinforcement learning we don't know the rewards associated to each state nor the probabilities to reach the various states associated to each action. This is what the algorithm need to discover (learn) by start "playing" autonomously.
+
+The correct answer is:
+  - None of the (other) sentences is correct
+
+```@raw html
+</details>
+```
+