Scribd
Upload
77 views34 pages

Lec1 Intoduction

This document provides an introduction to an artificial intelligence course on machine learning. It discusses supervised and unsupervised learning. Supervised learning involves labeled training data to predict discrete or continuous outputs. Unsupervised learning derives structure from unlabeled data by clustering based on variable relationships. The document provides examples of machine learning tasks like classification, regression, and examples of applications like facial recognition, medical imaging, and gene expression analysis.

Uploaded by

Ada Ika
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
77 views34 pages

Lec1 Intoduction

This document provides an introduction to an artificial intelligence course on machine learning. It discusses supervised and unsupervised learning. Supervised learning involves labeled training data to predict discrete or continuous outputs. Unsupervised learning derives structure from unlabeled data by clustering based on variable relationships. The document provides examples of machine learning tasks like classification, regression, and examples of applications like facial recognition, medical imaging, and gene expression analysis.

Uploaded by

Ada Ika
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 34

Artificial Intelligence Course

Introduction to machine
learning

Lec 1
Instructor:
Assoc Lecturer : Ahmed Yousry

Credits: This material is based mainly on Andrew NG’s Coursera ML course


•Peter Flach, Machine Learning. The Art and Science
of Algorithms that Make Sense of Data.

•T. Mitchell, Machine Learning,


McGraw-Hill

•John D. Kelleher, Fundamental of Machine Learning


for predictive Data Analytic.
Traditional Programming

Data
Output

Progra
Machine
m Learning

Data
Program
Output
Examples
Example 1 : Tic-Tac-Toe
Examples
Example 2 : face recognition
Examples
Example 3: Prediction of search queries
Examples
Example 4: Ranking search results
Examples
Example 5
Examples
Example 6
Examples
Example 7
Problem setup

So we need to separate

Tas Experience Performance


k
1- task

•Machine learning allows us to tackle tasks that are too


difficult to solve with fixed programs written and designed by
human beings.

•Machine learning is interesting because developing our


understanding of machine learning entails developing our
understanding of the principles that underlie intelligence.
1- task (Cont.)
Some of the most common machine learning tasks include
the following:

1 Classification : In his type of task, the computer program is


asked to specify which of k categories some input belongs to.
-Classification Algorithms attempt to map inputs into one of a set of
classes (Colors, Good and Bad Credit Risks)

2 Regression : In this type of task, the computer program is asked


to predict a numerical value given some input.
-Regression Algorithms attempt to mapinputs into continuous
output (Integers,Real Numbers, Vectors, etc.)
1- task (Cont.)
Some of the most common machine learning tasks include
the following:
3- Transcription: In this type of task, the machine learning system is
asked to observe a relatively unstructured representation of some kind
of data and transcribe it into discrete, textual form.

E.g.: optical character recognition (OCR), where the computer program is


shown a photograph containing an image of text and is asked to return
this text in the form of a sequence of characters.

4- Machine translation: In a machine translation task, the input


already consists of a sequence of symbols in some language, and the
computer program must convert this into a sequence of symbols in
another language.
2- Experience

• Experience is a dataset.

•A dataset is a collection of many examples.

• An example is a collection of features


that have been quantitatively measured
from
some object or event that we want the
machine learning system to process.
3- performance level

In order to evaluate the abilities of a machine learning algorithm,


we must design a quantitative measure of its performance.
Usually this performance measure P is specific to the task T
being carried out by the system.

- Accuracy : Accuracy is just the proportion of examples for


which the model produces the correct output.

- Error Rate : the proportion of examples for which the model


produces an incorrect output.
ML is used when:
 • Human expertise does not exist (navigating on Mars)
• Humans can’t explain their expertise (speech
recognition)
 • Models must be customized (personalized
medicine(
 • Models are based on huge amounts of data
(genomics)
Some more examples of tasks that are best
solved by using a learning algorithm

• Recognizing patterns:
– Facial identities or facial expressions
– Handwritten or spoken words
– Medical images
• Generating patterns:
– Generating images or motion sequences
• Recognizing anomalies:
– Unusual credit card transactions
– Unusual patterns of sensor readings in a nuclear power plant
• Prediction:
– Future stock prices or currency exchange rates
Slide credit: Geoffrey Hinton
Supervised Learning
In supervised learning, we are given a data set and already
know what our correct output should look like, having the
idea that there is a relationship between the input and the
output.
Supervised learning problems are categorized into "regression"
and "classification" problems.
In a regression problem, we are trying to predict results within
a continuous output, meaning that we are trying to map input
variables to some continuous function.
In a classification problem, we are instead trying to predict
results in a discrete output. In other words, we are trying to
Learning entries

Training
usually entries are encoded
Text, Images as vector (x1,x2,…..,xn)
Omic data, Featur
Etc… e
vectors Human expert labels
each learning entries

Machine
Labels learning
algorithm

Featur
Testing
e
Text, Images Expected
vector Predictiv
Omic data, e Label
Etc… Model
250

175

750

Supervised Learning Regression:

“right answers” or “Labeled data” Predict continuous valued output


given (price)
Lung Cancer
(Malignant or benging)

Classification

Discrete valued output (0 or 1)


Unsupervised Learning
 Unsupervised learning, on the other hand, allows us to
approach problems with little or no idea what our results
should look like.
We can derive structure from data where we don't
necessarily know the effect of the variables.
 We can derive this structure by clustering the
data based on
relationships among the variables in the data.
With unsupervised learning there is no feedback based on
the prediction results, i.e., there is no teacher to correct
you.
Y

X
Unsupervised

X
Unsupervised learning is where you only have input data
and no corresponding output variables.
Unsupervised Learning applications
The expression of set of genes for a
certain individual

Genes

Individuals
We need to cluster the individuals based of the similarity of
their genes.

[Source: Daphne Koller]


Unsupervised Learning applications

Genes

Individuals
Microarray data
• Have a group of individuals
• On each measure expression of a gene
• Run algorithm to cluster individuals into types of
people
[Source: Daphne Koller]
Learning Types

Supervised Unsupervised

Discrete
Classification Clustering
Continuous

Dimensionality
Regression
reduction
Machine Learning more types

You might also like