This document discusses machine learning (ML) and the ML process. It defines ML as a branch of artificial intelligence that uses computing systems to extract patterns from data and classify information. It describes supervised and unsupervised learning, with supervised learning using predefined outcomes to model feature-target relationships, and unsupervised learning finding relations in unlabeled data like clustering. The document outlines the ML process as defining objectives, preparing data through normalization and feature engineering, building models through training and validation sets, evaluating models, and deploying selected models. It emphasizes data preparation and proper data splitting, feature selection, and avoiding bias in model selection.

1. Machine Lg (ML)
• ML is a branch of artificial intelligence:
• Uses computing based systems to make sense
out of data
• Extracting patterns, fitting data to functions,
classifying
• ML systems can learn and improve
• With science and real noise data.
1

2. Supervised and Unsupervised Learning
• Unsupervised Learning
• There are not predefined and known set of outcomes
• relations in the data
• A typical example: Clustering
2
0.0
0.5
1.0
1.5
2.0
2.5
2 4 6
Petal.Length
Petal.Width
irisCluster$cluster
1
2
3

3. Supervised and Unsupervised Learning
• Supervised Learning
• For every example in the data there is always a predefined
outcome
• Models the relations between a set of descriptive features and
a target (Fits
• 2 groups of problems:
• Classification
• Regression
3

4. Machine Learning as a Process
Define
Objectives
Data
Preparation
Model
Building
Model
Evaluation
Model
Deployment
4
- Define measurable and quantifiable goals
- Use this stage to learn about the problem
- Normalization
- Transformation
- Missing Values
- Outliers
- Data Splitting
- Features Engineering
- Estimating Performance
- Evaluation and Model
Selection
- Study models accuracy
problem

5. ML as a Process: Data Preparation
5
• Needed for several reasons
• Some Models have strict data requirements
• not be underestimated
• Missing
Values
• Error Values
• Different
Scales
• Dimensionality
• Types
Problems
• Many others
Raw
Data
• Scaling
• Centering
• Skewness
• Outliers
• Missing
Values
• Errors
Data
Transfor
mation
Modeling
phase
Data
Ready

6. ML as a Process: Model Building
6
• Data Splitting
• Allocate data to different tasks
• model training
• performance evaluation
• Define Training, Validation and Test sets
• Feature Selection (Review the decision made previously)
• Estimating Performance
• Visualization of results – discovery interesting areas of the problem space
• Statistics and performance measures
• Evaluation and Model selection
• The ‘no free lunch’ theorem no a priory assumptions can be made
• Avoid use of favorite models if NEEDED