Machine Learning

unknownlippsΤεχνίτη Νοημοσύνη και Ρομποτική

16 Οκτ 2013 (πριν από 3 χρόνια και 8 μήνες)

49 εμφανίσεις

Machine Learning

Lecture 1

Course Information


Text book


Introduction to Machine
Learning
” by Ethem Alpaydin, MIT
Press.


Reference book


Data Mining
Introductory & Advanced Topics
” by
Margaret H. Dunham.


Course Objective


Introduction

to

the

basic

principles,

techniques,

and

applications

of

Machine

Learning

e
.
g
.



data
-
driven

knowledge

discovery

(data

mining)
.


Search

engine

architectures
.



Speech

recognition
.


Face

recognition
.



Preparation

of

job

skills

for

machine

learning


Be

able

to

conduct

original

research

in

machine

learning
.


Course Contents


Machine learning applications.


Supervised learning.


Bayesian decision theory.


Parametric methods.


Multivariate methods.


Principal Component Analysis.


Clustering

Course Contents contd.


Decision trees.


Linear discriminants.


Multilayer perceptrons.


Competitive learning & Radial Basis
Functions.


Hidden Markov Models.


Comparing Classification Algorithms.


Combining multiple learners.


Re
-
inforcement Learning


Grading Policy


Internal Marks

= 40


Lab performance

= 8 Marks


Assignments


=20 Marks


Theory Exams


=12 Marks



External Marks

= 10

Learning?


Intelligence

is

based

upon

learning
.


Learning

is

based

upon

past

experience

and

knowledge

about

the

problem
.



Prediction



we

make

predictions

all

the

times

but

rarely

investigate

the

underlying

process
.


Specific

knowledge

(data)

processing

approach

for

a

particular

problem
.




Machine Learning?


Machine

Learning

is

subfield

of

Artificial

Intelligence

concerned

with

design

and

development

of

algorithms

and

techniques

that

allow

computers

to

learn

(
Wikipedia
)
.



Machine

learning

is

area

of

AI

that

examines

how

to

write

programs

that

can

learn
.


Components in Machine
Learning


Data acquisition
or

Knowledge from Experts.



Development of Training Data
or

Rules .



Specific model development.

Applications of Machine
Learning


Data mining.


Search engines.


Game playing.


Object recognition.


Robot locomotion.


Bioinformatics.


Cheminformatics.


Natural language processing etc.


Data Mining


Data

Mining

is

a

set

of

processes

related

to

analyzing

and

discovering

useful,

actionable

knowledge

buried

deep

beneath

large

volumes

of

data

sets
.



Typical Job Structures of
Machine Learning Professionals


Object Oriented Programming


C++


Perl


Python


Smaltalk


Database environments


Lotus.


SQL server.


Excel.


Oracle.


Machine Learning Concepts.