Scribd
Upload
18 views12 pages

Lect01-Introduction To ML

This document provides an introduction to machine learning. It defines machine learning as enabling computers to learn from experience with respect to a task and performance measure. The document discusses how machine learning is a subfield of artificial intelligence that allows computers to learn from data and statistics. It also defines the key components of a learning task as the task, the performance metric, and experience. The document concludes by discussing the different types of machine learning, including supervised, reinforcement, and unsupervised learning.

Uploaded by

shehzad shafique51
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
18 views12 pages

Lect01-Introduction To ML

This document provides an introduction to machine learning. It defines machine learning as enabling computers to learn from experience with respect to a task and performance measure. The document discusses how machine learning is a subfield of artificial intelligence that allows computers to learn from data and statistics. It also defines the key components of a learning task as the task, the performance metric, and experience. The document concludes by discussing the different types of machine learning, including supervised, reinforcement, and unsupervised learning.

Uploaded by

shehzad shafique51
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 12

Introduction to

Machine learning Machine


Learning(ML)
Course Code:CS467
Dr. Muhammad Abid
Assistant Professor
Govt: Postgraduate
College Kohat
Introduction to Course
2

 In this course we will go back to mathematics


and study statistics, and how to calculate
important numbers based on data sets.
 We will also learn how to use various Python
modules to get the answers we need.
 And we will learn how to make functions that
are able to predict the outcome based on
what we have learned.
What is machine learning?
3

 Machine learning adapts to the user based on data


 Online shopping(visiting amazon for 1st time, Machine is learning at
that time and the 2nd time when u r visiting he will give you some
recommendations etc.)
 Machine learning is a sub-field of artificial intelligence. Its goal is
to enable computers to learn on their own.

 “A computer program is said to learn from experience E with


respect to some task T and some performance measure P, if its
performance on T, as measured by P, improves with experience E.”
“Tom Mitchell”
Defining the Learning Task
4

 Improve on task T, with respect to performance metric P, based on


experience E
 An agent solves a task T, Performance P and gain some experience
E
 For example: Playing checker game

 T: Playing checkers
 P: Percentage of games won against an arbitrary opponent
 E: Playing practice games against itself

Hand written recognition Problem


 T: Recognizing hand-written words
 P: Percentage of words correctly classified
 E: Database of human-labeled images of handwritten words
Defining the Learning Task
5
What is machine learning?
6

 Machine Learning is making the computer


learn from studying data and statistics.
 Machine Learning is a step into the direction
of artificial intelligence (AI).
 Machine Learning is a program that analyses
data and learns to predict the outcome.
What is Learning?
7

 Herbert Simon: “Learning is any process by


which a system improves performance from
experience.”
What is machine learning?
8

 AI(It enables the machine to think)


 ML(It provides statistical

tools to explore the data)


 DL(Create architecture)
Examples of tasks that are best solved
by using a learning algorithm
9

 Recognizing patterns:
 Facial identities or facial expressions
 Handwritten or spoken words
 Medical images
 Generating patterns:
 Generating images
 Recognizing anomalies:
 Unusual credit card transactions
 Unusual patterns of sensor readings in a nuclear power
plant
 Prediction:
 Future stock prices or currency exchange rates
Types of machine learning
10
Types of machine learning
11

 Supervised learning: uses a series of labelled


examples with direct feedback
 Someone gives us examples and the right answer for those
examples
 We have to predict the right answer for unseen examples
 Reinforcement learning: indirect feedback, after
many examples
 We take actions and get rewards
 Have to learn how to get high rewards
 Unsupervised/clustering learning:
 We see examples but get no feedback
 We need to find patterns in the data
Thanks

You might also like