Chapter 5 AI
Chapter 5 AI
1/24/2024 2
Why Machine Learning ?
There may not be rules that are both simple and reliable.
We need to combine a very large number of weak rules.
1/24/2024 4
Why Machine Learning ?
1/24/2024 5
Why Machine Learning ?
1/24/2024 6
Why Machine Learning ?
A more engineering-oriented:
A computer program is said to learn from experience E with
respect to some class of task T and performance measure P, if its
performance at task in T, as measured by P, improves with
experience E. (Tom Mitchell – 1998)
1/24/2024 8
What is Machine Learning ?
1/24/2024 9
Examples of ML Application
1/24/2024 12
ML related to this Course
Some prerequisite :
Programming (python, matlab, R etc…)
Probability and Statistics;
Mathematics (Linear Algebra, Matrix, Vector, differential
calculus, and integral calculus)
Curiosity of working with data etc… (most importantly)
1/24/2024 13
Learning Path
1/24/2024 14
Learning Path
1/24/2024 15
Learning Path
1/24/2024 16
Learning Path
1/24/2024 17
Learning Path
1/24/2024 18
Learning Path
1/24/2024 19
Machine Learning systems
1/24/2024 21
Supervised Learning
1/24/2024 22
Supervised Learning
1/24/2024 23
Supervised Learning
Input 1 2 3 4 5 6 9
Output 1 4 9 16 25 36 ?
Supervised Learning:
Regression Problem: numerical / continuous value.
Given some data, you assume that those values come from some
sort of function and try to find out what the function is.
It is a problem of function approximation or interpolation.
1/24/2024 25
Supervised Learning
1/24/2024 26
Unsupervised Learning
Unsupervised learning :
Unsupervised (concise description) [cluster scores well]
The aim of unsupervised learning is to find clusters of
similar inputs in the data without being explicitly told that some
data points belong to one class and the other in other classes.
1/24/2024 27
Unsupervised Learning
1/24/2024 28
Unsupervised Learning
1/24/2024 29
Unsupervised Learning
1/24/2024 30
Reinforcement Learning
Reinforcement learning :
Reinforcement (stimulus/state, action, reward) [behavior scores
well] – reward maximization.
The algorithm searches over the state space of possible inputs and
outputs in order to maximize a reward.
Learn to select an action to maximize payoff.
1/24/2024 31
Reinforcement Learning
1/24/2024 32
Machine Learning Vs AI
1/24/2024 33
Machine Learning Vs AI
1/24/2024 34
Machine Learning Application
1/24/2024 35
Machine Learning
1/24/2024 36
Machine Learning
1/24/2024 37
Machine Learning
1/24/2024 38
Question & Answer
1/24/2024 39
Thank You !!!
1/24/2024 40