Machine Learning

First Meet – Introduction [ADF19]

Agung Toto Wibowo

[email protected]

WA: 081322513875

IG: atwbox

Fb : Agung Toto

http://agungtoto.web.id

1 10/11/2022
Today’s Agenda
Introduction

Brief history of Machine Learning

2 10/11/2022 Machine Learning

Course Introduction
Course Name: Machine Learning
– Supervised,
– Unsupervised,
– Ensembles

Course Code: CII3C3

Credits : 3
14 weeks of each:
– 3 x 50’ class
– 3 x 50’ structured tasks
– 3 x 50’ self study

3 10/11/2022 Machine Learning

Pre-requisite
Proficiency in Algorithm and Programming
– Basic Algorithm and Programming
– Algorithm Analysis and Design
– Calculus

Linear Algebra

Probabilistic and Statistics

Artificial Intelligence

4 10/11/2022 Machine Learning

Course Objectives
Students are able to explain the concept of each machine
learning method.

Students are able to identify, model, analyze and solve

problems using machine learning methods.

Students are able to implement machine learning methods

using programming languages to solve problems.

5 10/11/2022 Machine Learning

Syllabus & CLO
Lets Open the RPS

6 10/11/2022 Machine Learning

Scoring
Komponen Penilaian: a. 60% Tugas Besar, b. 10%
Kuis/Tugas Dosen (4x)

Tugas Besar
– hanya ada 1 tugas mencakup Unsupervised, Supervised, dan
Ensemble dengan 1 kasus (dataset)
– Unsupervised: Melakukan clustering dg k-means (program
dibangun dari awal)
– Supervised: Melakukan regresi atau klasifikasi, metode bebas,
boleh library
– Tugas diberikan saat/setelah masa UTSs
– Penilaian oleh dosen pada 2 pertemuan presentasi
NO MID/FINAL EXAM
7 10/11/2022 Machine Learning
Final Points

A 80 … 100.0
AB 75 … 79.99
B 70 … 74.99
BC 60 … 69.99
C 50 … 59.99
D 40 … 49.99
E 0 ... 39.99

8 10/11/2022 Machine Learning

 Academic Honesty
and
Collaboration policy

9 10/11/2022 Convolutional Neural Network

Rule 1
Don’t look at solutions or code that are not your own

Everything you submit should be your own work

10 10/11/2022 Convolutional Neural Network

Rule 2
Don’t share your solution code with others

However discussing ideas or general strategies is fine and

encouraged

11 10/11/2022 Convolutional Neural Network

Rule 3
Be responsible with your attendance

Any kind of Cheating and Plagiarism is not acceptable

and will not be forgiven

Maintain the appropriate condition in the class

– Mind your manners and attitudes
– You may bring snacks and drinks
but please no noisy or strong-smelling ones
– Drowsy? Just sleep quietly

Language?

12 10/11/2022 Machine Learning

 Turning in something late/incomplete
is better than
violating the honor code

13 10/11/2022 Convolutional Neural Network

Link
anditya.staff.telkomuniversity.ac.id/academic/mcl

14 10/11/2022 Machine Learning

References
[1] Suyanto, "Machine Learning: Tingkat Dasar dan Lanjut",
Penerbit Informatika, Bandung, 2018

[2] Miroslav Kubat, "An Introduction to Machine Learninge" Second

Edition, Springer, 2017.

[3] Suyanto, "Data Mining untuk Klasifikasi dan Klasterisasi Data",

Penerbit Informatika, Bandung, 2017.

[4] Suyanto, "Deep Learning: Modernisasi Machine Learning untuk

Big Data", Penerbit Informatika, Bandung, 2019.

[5] Max Bramer, "Principles of Data Mining" Third Edition, Springer,

2017.

[6] Richard S. Sutton and Andrew G. Barto, "Reinforcement

Learning - An Introduction" Second Edition, The MIT Press,
15 Cambridge,
10/11/2022 Massachusetts, London, England, 2020 Machine Learning
 Introduction to Machine Learning

16 10/11/2022 Machine Learning

What is Machine Learning?
Machine
– computer, computer program (in this course)

Learning
– improving performance on a given task,
based on experience / examples

Machine Learning
– concerned with computer programs that automatically improve
their performance through experience

17 10/11/2022 Machine Learning

What is Machine Learning?
Very hard to write programs that solve problems

Example:
Recognizing three-dimensional object
– Don’t know how it’s done in our brain 
don’t know what to write
– Even if we had a good idea about how to do it,
program might be horrendously complicated

18 10/11/2022 Machine Learning

What is Machine Learning?
Instead of the programmer writing explicit rules for how to
solve a given problem,

We collect lots of examples that specify

the correct output for a given input

The programmer instructs the computer

how to learn from examples

19 10/11/2022 Machine Learning

What is Machine Learning?
The program produced may look very different from a
typical hand-written program

In many cases the computer program

can even become better at the task
than the programmer is!

Massive amount of computation are

now cheaper than paying someone to write
a task-specific program

20 10/11/2022 Machine Learning

Learn from Data
One definition of machine learning:
A computer program improves its performance on a given
task with experience
(i.e. examples, data).

Thus we need to separate:

– Task: What is the problem that the program is solving?
– Performance measure: How is the performance of the
program (when solving the given task) evaluated?
– Experience: What is the data (examples) that the program is
using to improve its performance?

21 10/11/2022 Machine Learning

Availability of data
These days it is very easy to
– collect data (sensors are cheap, much information digital)
– store data (hard drives are big and cheap)
– transmit data (essentially free on the internet).

But how to benefit from it?

Analysis is becoming key!

22 10/11/2022 Machine Learning

 Machine Learning Taxonomy

27 10/11/2022 Machine Learning

 Deep Learning Example:
Shallow
Example: autoencoders Example: Example:
MLPs Logistic Knowledge
regression bases

Representation
Learning

Machine Learning

AI
28 10/11/2022 Machine Learning
Machine Learning Taxonomy
Supervised Learning

Unsupervised Learning

Reinforcement Learning

29 10/11/2022 Machine Learning

30 10/11/2022 Machine Learning
Supervised Learning
we have a data set that includes the target values (the
values we wish to predict).

try to learn a function that correctly maps the target values

from the other features, which can then be used to make
predictions about other examples.

Two flavors:
– Classification: output is label
– Regression: output is value

31 10/11/2022 Machine Learning

32 10/11/2022 Machine Learning
Unsupervised Learning
We have a dataset but there is no target to be predicted.

Discover a good internal representation of the input

Example: clustering, density estimation, noise reduction.

Semi-Supervised

33 10/11/2022 Machine Learning

34 10/11/2022 Machine Learning
Reinforcement Learning
Learn to select an action to maximize payoff (future rewards)

A reward and punishment function is provided that tells us

how “good” certain states/actions are.

Making a decision now influences what decisions

we can make in the future.

35 10/11/2022 Machine Learning

Ensembles Method
use multiple learning algorithms to obtain better predictive
performance than could be obtained from any of the
constituent learning algorithms alone

36 10/11/2022 Machine Learning

37 10/11/2022 Machine Learning
 Examples

38 10/11/2022 Machine Learning

Tic-Tac-Toe

How to program
the computer to
play tic-tac-toe?

39 10/11/2022 Machine Learning

Tic-Tac-Toe
How to program the computer to play tic-tac-toe?

Option A: The programmer writes explicit rules, e.g. 'if the

opponent has two in a row, and the third is free, stop it by
placing your mark there', etc.
(lots of work, difficult, not at all scalable!)

Option B: Go through the game tree, choose optimally

(for non-trivial games, must be combined with some
heuristics to restrict tree size)

40 10/11/2022 Machine Learning

Tic-Tac-Toe
How to program the computer to play tic-tac-toe?

Option C:
Let the computer try out various strategies by playing
against itself and others, and noting which strategies lead to
winning and which to losing (='machine learning')

41 10/11/2022 Machine Learning

Checker Game
Arthur Samuel (50's and 60's):

Computer program that learns to play checkers

Program plays against itself thousands of times, learns

which positions are good and which are bad
(i.e. which lead to winning and which to losing)

The computer program eventually

becomes much better than
the programmer.

42 10/11/2022 Machine Learning

Spam Filtering
Traditional: Programmer writes rules:
– ex: If it contains 'viagra' then it is spam.
– (difficult, not user-adaptive)

Machine Learning:
– The user marks which mails are spam, which are legit, and the
computer learns itself what words are predictive

43 10/11/2022 Machine Learning

Prediction of search queries
Traditional:
– The programmer
provides a standard
dictionary
– (words and expressions
change!)

Machine Learning:
– Previous search queries
are used as examples!

44 10/11/2022 Machine Learning

Detecting credit card fraud
Credit card companies typically end up paying for fraud
(stolen cards, stolen card numbers)

Useful to try to detect fraud, for instance large transactions

Important to be adaptive to the behaviors of customers,

i.e. learn from existing data how users normally behave,
and try to detect 'unusual' transactions

45 10/11/2022 Machine Learning

Character recognition
Automatically sorting mail (handwritten characters)

Digitizing old books and newspapers into easily searchable

format (printed characters)

46 10/11/2022 Machine Learning

Face Recognition
Traditional: Programmer writes rules:
– ex: If short dark hair, big nose, then it is Alex
– (impossible! how do we judge the size of the nose?!)

Machine Learning:
– The computer is shown many (image, name) example pairs, and
the computer learns which features of the images are predictive
(difficult, but not impossible)

47 10/11/2022 Machine Learning

Character recognition

48 10/11/2022 Machine Learning

Self-driving cars
Sensors (radars, cameras) superior to humans

How to make the computer react appropriately to the sensor

data?

49 10/11/2022 Machine Learning

Social Media Analysis
Mining chat and discussion forums
– Breaking news
– Detecting outbreaks of infectious disease
– Tracking consumer sentiment about companies / products
– Prediction of friends in Facebook, or prediction of who you’d like
to follow on Twitter.

50 10/11/2022
Machine Translation
Traditional:
– Dictionary and explicit grammar

Machine Learning:
– statistical machine translation based on example data is
increasingly being used

51 10/11/2022 Machine Learning

Automatic Speech Recognition
recognize human speech, so that the computer can listen,
write, understand, even answer the user's speech

Text-to-Speech

Google Duplex

52 10/11/2022 Machine Learning

 Todays AI

53 10/11/2022 Artificial Intelligence

Todays AI
[2011] IBM’s Watson won a game of Jeopardy against the
top two all-time champions

[2015-2018] Neural Net beat human accuracy in 1000-class

Visual Recognition in IMAGENET

54 10/11/2022
Deep Mind’s AlphaGo
the first computer program to defeat a professional human
Go player

1st version: used a dataset of more than 100,000 Go games

as a starting point for its own knowledge

Win 4-1 vs Lee Sedol in 2016

– one of the strongest players
in the history of Go
– Awarded an "honorary 9 dan"

55 10/11/2022 Machine Learning

Deep Mind’s AlphaGo Zero
2nd version of AlphaGo: Learning from scratch

Reinforcement Learning
– a version without human data and stronger than any previous
human-champion-defeating version only by playing games
against itself
– Faster training to reach the same level

Win 2-1 vs Ke Jie in 2017

– current world No. 1 ranking player

56 10/11/2022 Machine Learning

Todays AI
[2017] DeepBlue beat poker pro players

[2017] Elon Musk’s OpenAI Dota2 bot beat pro player

[2018] A portrait created by AI just sold for $432,000.

[2018] Video to Video Synthesis

57 10/11/2022
Question?

58 10/11/2022 Machine Learning

 THANK YOU
10/11/2022
59