Machine learning is a branch of artificial intelligence focused on developing algorithms that enable computers to learn from empirical data. It encompasses various types of learning, including supervised, unsupervised, semi-supervised, and reinforcement learning, and relies on algorithms to extract useful information from training data. Practical applications range from face and object detection to spam filtering and web advertising.

1. Machine Learning

2. What is Machine Learning
Definition of machine learning is in it’s name
Machine + Learning
Means
Machine is learning
By What & How?
By Fetched(Input) data and Past Experience

3. • Traditional Programming
Data
Output
Program
• Machine Learning
Data
Program
Output
Computer

4. Machine learning
definition
• A branch of artificial intelligence, concerned with the design
and development of algorithms that allow computers to evolve
behaviors based on empirical data.
• As intelligence requires knowledge, it is necessary for the
computers to acquire knowledge.

5. Types of learning
• Supervised (inductive) learning
– Training data includes desired outputs
• Unsupervised learning
– Training data does not include desired outputs
• Semi-supervised learning
– Training data includes a few desired outputs
• Reinforcement learning
– Rewards from sequence of actions

6. Training and testing
Training set
(observed)
Universal set
(unobserved)
Testing set
(unobserved)
Data acquisition Practical usage

7. • Training is the process of making the system able to learn.
• No free lunch rule:
o Training set and testing set come from the same distribution
o Need to make some assumptions or bias
Training and testing

8. Algorithms
• The success of machine learning system also depends on the
algorithms.
• The algorithms control the search to find and build the
knowledge structures.
• The learning algorithms should extract useful information
from training examples.

9. List of Common Machine
Learning Algorithms
• Linear Regression
• Logistic Regression
• Decision Tree
• SVM
• Naive Bayes
• kNN
• K-Means
• Random Forest

10. Applications
• Face detection
• Object detection and recognition
• Image segmentation
• Multimedia event detection
• Spam and fraud detection
• Web Advertising