ML

Question 1

Learning definition

Answer 1

“Learning is any process by which a system improves performance from experience.”

Question 2

ML definition

Answer 2

Machine Learning is the study of algorithms that:
* improve their performance P
* at some task T
* with experience E
A well-defined learning task is given by <P, T, E>.

Question 3

Difference btwn traditional programming and ML

Question 4

Why is ML needed?

Question 5

Skills required for ML

Answer 5

Machine Learning requires:
- Mathematics
- Algorithms
- Programming
Otherwise, you may just use it as a black box

Question 6

Steps 2 design ML system

Answer 6

1. Formulating the problem (the learning task)
2. Data collection
3. Features extraction
4. Choosing the suitable class of learning model
5. Training the model
6. Model evaluation

Question 7

Types of ML

Answer 7

Supervised Learning:
- Given: training data + desired outputs (labels)
- Unsupervised Learning:
- Given: training data (without labels)
- Reinforcement Learning:
- Given: observations and periodic rewards as the agent takes sequential action in an
environment

Question 8

What is supervised learning

Question 9

Types of supervised learning

Question 10

Real life examples of regression

Answer 10

• Medical field: understanding the relationship between drug dosage and the blood pressure of
  patients.
• Agriculture field: measuring the effect of fertilizer and water on crop yields.
• Businesses: understanding the relationship between advertising spending and revenue.
• Real Estate Industry: predicting house prices while considering some features such as the area
  of the house, the number of rooms, the view, etc.

Question 11

Regression algorithms

Answer 11

• Linear Regression
• Regression Trees
• Random Forest
• K-Nearest Neighbors (KNN)
• Support Vector Regression (SVR)

Question 12

classification algorithms

Answer 12

• Logistic Regression
• K-Nearest Neighbors (KNN)
• Support Vector Machine (SVM)
• Decision Trees

Question 13

evaluation matrices 4 regression

Answer 13

• Mean Absolute Error
• Mean Squared Error
• Root Mean Squared Error
• Explained Variance

Question 14

evaluation matrices 4 classification

Answer 14

• True positives:
• True negatives:
• False positives:
• False negatives:

Question 15

formulas of mean squared error; accuracy; precision; recall

Answer 15

mse = 1/all*sum(true-pred)^2
accuracy = correct prediction / all
precision = TP/TP+FP
recall = TP/TP+FN