SIT1305- MACHINE LEARNING

TEXT / REFERENCE BOOKS

Ethem Alpaydin, “Introduction to Machine
Learning”, MIT Press,2004
Tom Mitchell, “Machine Learning”, McGraw Hill,
1997.
 UNIT 1 INTRODUCTION TO MACHINE
LEARNING

• Machine learning - examples of machine

learning applications - Learning associations -
Classification - Regression - Unsupervised
learning - Supervised Learning - Learning
class from examples - PAC learning -
Noise,model selection and generalization -
Dimension of supervised machine learning
algorithm.
 What is machine learning?

• A branch of artificial intelligence, concerned

with the design and development of
algorithms that allow computers to evolve
behaviors based on empirical data.

• As intelligence requires knowledge, it is

necessary for the computers to acquire
knowledge.

3
 What is Machine Learning?
Aspect of AI: creates knowledge

Definition:
“changes in [a] system that ... enable [it] to do the same task or
tasks drawn from the same population more efficiently and
more effectively the next time.'' (Simon 1983)
There are two ways that a system can improve:
1. By acquiring new knowledge
– acquiring new facts
– acquiring new skills
2. By adapting its behavior
– solving problems more accurately
– solving problems more efficiently

4
 What is Learning?
• Herbert Simon: “Learning is any process by
which a system improves performance from
experience.”
• What is the task?
– Classification
– Categorization/clustering
– Problem solving / planning / control
– Prediction
– others

5
Artificial Intelligence

6
 Multidisciplinary Field
data
mining control theory

statistics
decision theory
information theory machine
learning
cognitive science
databases
psychological models
evolutionary neuroscience
models

Machine learning is primarily concerned with the accuracy

and effectiveness of the computer system.

7
 What Machine Learning can do
 Finding which category an object belongs to -- by
Classification Algorithm
 Finding what is strange -- by Anomaly Detection
Algorithm
 Finding how much and how many -- by
Regression Algorithm
 Finding how data is arranged – by Clustering
Algorithm
 What should I do next -- by Reinforcement
Algorithm

8
 Understanding Machine Learning
Machine Learning vs Statistical Inference vs Pattern
Recognition vs Data Mining

Perspective 1
same concepts evolving in different scientific traditions
• Statistical Inference (SI): field of Applied Mathematics
• Machine Learning (ML): field of AI
• Pattern Recognition (PR): branch of Computer Science
focused on perception problems (image processing,
speech recognition, etc.)
• Data Mining (DM): field of Database Engineering

9
 Understanding Machine Learning
Perspective 2: slight conceptual differences
• Statistical Inference: inference based on probabilistic
models built on data. Located at the intersection of
Mathematics and Artificial Intelligence (AI)
• Machine Learning: methods tend to be more heuristic in
nature
• Pattern Recognition: most authors defend it is the same
thing as machine learning
• Data Mining: applied machine learning. Involves issues such
as data pre-processing, data cleaning, transformation,
integration or visualization. Involves machine learning, plus
computer science and database systems. 10

10
 Why Machine Learning?
• No human experts
– industrial/manufacturing control
– mass spectrometer analysis, drug design, astronomic
discovery
• Black-box human expertise
– face/handwriting/speech recognition
– driving a car, flying a plane
• Rapidly changing phenomena
– credit scoring, financial modeling
– diagnosis, fraud detection
• Need for customization/personalization
– personalized news reader
– movie/book recommendation

11
Machine Learning Trends

12
 Machine Learning Trends
“Telephone took 75 years to reach 50
million users, radio 38 yrs, television
13 yrs, Internet 4 yrs, Facebook 19
months, Pokemon Go 19 days.
AarogyaSetu, India’s app to fight
COVID-19 has reached 50 mn users in
just 13 days-fastest ever globally for
an App,” Kant said in his tweet.

The app will calculate this based on their interaction with

others, using cutting edge Bluetooth technology, algorithms
and artificial intelligence.
13
 Designing a Learning System
• Choose the training experience
• Choose exactly what is too be learned, i.e. the target
function.
• Choose how to represent the target function.
• Choose a learning algorithm to infer the target
function from the experience.
Learner

Environment/
Knowledge
Experience

Performance
Element

14
Machine Learning Workflow

15
Types of Machine Learning

16
 Learning Paradigms
Supervised learning
– Generates a function that maps inputs to desired
outputs.
• For example, in a classification problem, the
learner approximates a function mapping a
vector into classes by looking at input-output
examples of the function
– Probably, the most common paradigm
– E.g., decision trees, support vector machines, Naïve
Bayes, k-Nearest Neighbors, …
17

17
 Machine learning structure
• Supervised learning

18
 Learning Paradigms
• Unsupervised learning
– Labels are not known during training
– E.g., clustering, association learning

• Semi-supervised learning
– Combines both labeled and unlabeled examples to
generate an appropriate function or classifier
– E.g., Transductive Support Vector Machine

19

19
 Machine learning structure
• Unsupervised learning

20
 Machine learning structure
• semisupervised learning

The goal of a semi-supervised model is to classify some of the

unlabeled data using the labeled information set.

•Speech Analysis
•Protein Sequencing
•Web content analysis
21
 Reinforcement Learning

• In the absence of training dataset, it is bound to learn from its

experience.
• We have an agent and a reward, with many hurdles in between.
The agent is supposed to find the best possible path to reach the
reward.

Types of Reinforcement: positive, negative, punishment, and

extinction.
22
 Machine learning structure
• Reinforcement learning

– It is concerned with how an agent should take actions in an

environment so as to maximize some notion of cumulative
reward.
• Reward given if some evaluation metric improved
• Punishment in the reverse case
– E.g., Q-learning, Sarsa
23
Machine Learning Perspectives

24
 Algorithms
• Supervised learning
– Prediction
– Classification (discrete labels), Regression (real values)
• Unsupervised learning
– Clustering
– Probability distribution estimation
– Finding association (in features)
– Dimension reduction
• Semi-supervised learning
• Reinforcement learning
– Decision making (robot, chess machine)
25
 ML Algorithms
• Classification
– Learn a way to classify unseen examples, based on a
set of labeled examples, e.g., classify songs by
emotion categories. E.g., decision trees (e.g., C5.4)

• Regression
– Learn a way to predict continuous output values,
based on a set of labeled examples, e.g., predict
software development effort in person months
– Sometimes regarded as numeric classification
(outputs are continuous instead of discrete) 26

– E.g., Support Vector Regression 26

 ML Algorithms
• Association
– Find any association among features, not just input-
output associations (e.g., in a supermarket, find that
clients who buys apples also buys cereals)
– E.g., Apriori

• Clustering
– Find natural grouping among data
– E.g., K-means clustering, DBSCAN, Heirarchial
clustering
27

27
Machine Learning Process

28
 Training and testing
• Training is the process of making the system able to learn.
• No free lunch rule:
– Training set and testing set come from the same distribution
– Need to make some assumptions or bias

29
 Performance
• There are several factors affecting the performance:
– Types of training provided
– The form and extent of any initial background
knowledge
– The type of feedback provided
– The learning algorithms used

• Two important factors:

– Modeling
– Optimization
30
 Machine Learning Traditions
• Different ML traditions propose different approaches
inspired by real-world analogies
– Neural networks researchers: emphasize analogies
to neurobiology
– Case-based learning: human memory
– Genetic algorithms: evolution
– Rule induction: heuristic search
– Analytic methods: reasoning in formal logic
• Again, different notation and terminology

31

31
Different Varieties of Machine Learning
• Concept Learning
• Clustering Algorithms
• Connectionist Algorithms
• Genetic Algorithms
• Explanation-based Learning
• Transformation-based Learning
• Reinforcement Learning
• Case-based Learning
• Macro Learning
• Evaluation Functions
• Cognitive Learning Architectures
• Constructive Induction
• Discovery Systems
• Knowledge capture
32
 Learning Paradigms
• Black-box
– Learned model internals are practically incomprehensible
• E.g., Neural Networks, Support Vector Machines
• Transparent-box
– Learned model internals are understandable, interpretable
• E.g., explicit rules, decision-trees
• Instance-based or case-based learning
– Represents knowledge in terms of specific cases or
experiences
– Relies on flexible matching methods to retrieve these cases
and apply them to new situations
– E.g., k-Nearest Neighbors
33

33
Machine Learning Applications

34
Machine Learning touching our Daily Life
Walmart use Robots in
their stores for inventory
management, packing,
pricing checks

Restaurants
have Robot
chefs and
Waiters

35
 Machine Learning touching our Daily Life

Michelangelo, an internal ML-as-a-service platform that

democratizes machine learning and makes scaling AI to
meet the needs of business as easy as requesting a ride.
36
Machine Learning touching our Daily Life

Song Recommendations
based on mood and interest

Data Acquisition from Tamr – Enterprise

Data Unification Company

Content specific
vaccines for Children

37
Amazon – Game Changer of the Decade

38
Machine Learning in Civil Engineering
 Design of Construction Management System
 Prediction of the Severity of Earthquakes
 Better analysis of monitoring the construction
health
 Analysis of Environmental Engineering
 Design of Highway and transportation
Engineering fo the prediction of Transport arrivals
and pedestrian movement analysis
 Use of Machine learning in surveying,
Geotechnical and Geospatial Engineering
39
Machine Learning in Mechanical
Engineering
 Cognitive Science of a Machine
 Use of IoT and Big Data Analytics
 On site performance of devices
 Non-linear root cause analysis
 Tools for analytics and operations

40
Autonomous Cars - ALVINN

41
Autonomous Driving Cars

42
43
 Adaptive Highbeam
Automatically and
continuously
adapts the
headlamp range
to the distance of
vehicles ahead or
which are
incoming
44
 Predicting mechanical failure
• By continuously monitoring data (power plant,
manufacturing unit operations) and providing
them to smart decision support systems,
manufacturers can predict the probability of
failure.

• Predictive maintenance is an emerging field in

industrial applications that helps in determining
the condition of in-service equipment to estimate
the optimum time of maintenance.

• ML-based predictive maintenance saves cost

and time on routine or preventive maintenance.
45
 AI for automatically segmenting brain
tumors
Artificial Intelligence has a broad scope in
healthcare devices and applications.

Makes analysis, treatment, and monitoring of

tumors more effective.

NVIDIA has developed a 3D MRI brain tumor

segmentation using deep-learning and 3D magnetic
resonance imaging technologies.

46
Chat bots
Internet of Things
 Personalization

Sophia Google Assistant

social humanoid
Amazon Alexa
Virtual Assistant
Personalization Platforms

49
Machine Learning Applications across Industries

50
Investment in Robotics
 Robotics and ML
Areas that robots are used:
Industrial robots
Military, government and space robots
Service robots for home, healthcare, laboratory
Why are robots used?
Dangerous tasks or in hazardous environments
Repetitive tasks
High precision tasks or those requiring high quality
Labor savings
Control technologies:
Autonomous (self-controlled), tele-operated (remote
control)
52
 Industrial Robots
• Uses for robots in manufacturing:
– Welding
– Painting
– Cutting
– Dispensing
– Assembly
– Polishing/Finishing
– Material Handling
• Packaging, Palletizing
• Machine loading

53
 Industrial Robots
• Uses for robots in industry/Manufacturing
– Automotive
– Packaging

54
 Military/Government Robots

• iRobot PackBot

Remotec Andros

55
 Military/Government Robots

Soldiers in Afghanistan being trained how to defuse a landmine using a PackBot.

56
 Military Robots
Military suit
• Aerial drones (UAV)

57
 Space Robots
• Mars Rovers – Spirit and Opportunity
– Autonomous navigation features with human
remote control and oversight

58
 Service Robots
• Many uses…
– Cleaning & Housekeeping
– Humanitarian Demining
– Rehabilitation
– Inspection
– Agriculture & Harvesting
– Lawn Mowers
– Surveillance
– Mining Applications
– Construction
– Automatic Refilling
– Fire Fighters
– Search & Rescue
iRobot Roomba vacuum cleaner robot
59
 Medical/Healthcare Applications
DaVinci surgical robot by Intuitive Surgical. Japanese health care assistant suit
St. Elizabeth Hospital is one of the local hospitals using this robot. You can
see this robot in person during an open house (website). (HAL - Hybrid Assistive Limb)

Also… Mind-controlled
wheelchair using NI LabVIEW

60
 Laboratory Applications

Drug discovery Test tube sorting

61
AI vs Machine Learning vs Deep Learning
Programs with the ability
to learn and reason like
humans

Algorithms with the ability

to learn without being
explicitly programmed

Subset of Machine
Learning in which Artificial
Neural Networks adapt
and learn from vast
amounts of data.

63
Deep Learning

64
Machine Intelligence Landscape

65
 Future of machine learning
• Improved unsupervised algorithms
• Enhanced personalization
• Increased adoption of quantum
computing
• Improved cognitive services
• Rise of robots

66
Future of Machine Learning
Gartner Predictions

67
Technology Trends 2020

68
Industry 4.0 the Future

69
Skills Required

70
Top Machine Learning Software Tools
Written in
Software Platform Algorithms or Features
language
Scikit Learn Linux, Mac OS, Python, Classification, Regression
Windows Cython, C, C+Clustering, Preprocessing
+ Model Selection
Dimensionality reduction.
PyTorch Linux, Mac OS, Python, C++, Autograd Module, Optim
Windows CUDA Module, nn Module
TensorFlow Linux, Mac OS, Python, C++, Provides a library for dataflow
Windows CUDA programming.
Weka Linux, Mac OS, Java Data preparation, Classification
Waikato Windows Regression, Clustering
Environment Visualization, Association rules
for mining
Knowledge
Analysis
71
Top Machine Learning Software Tools
Written in
Software Platform Algorithms or Features
language
KNIME Linux, Mac Java Can work with large data volume.
Konstanz OS, Supports text mining & image
Information Windows mining through plugins
Miner
Colab Cloud - Supports libraries of PyTorch,
Service Keras, TensorFlow, and OpenCV
Apache Cross- Java Preprocessors, Regression
Mahout platform Scala Clustering, Recommenders
Distributed Linear Algebra.
Accors.Net Cross- C# Classification, Regression,
platform Distribution, Clustering
Hypothesis Tests & Kernel
Methods, Image, Audio & Signal.
& Vision
72
Top Machine Learning Software Tools
Written in
Software Platform Algorithms or Features
language
Shogun Windows C++ Regression, Classification
Linux Clustering, Support vector
UNIX machines, Dimensionality
Mac OS reduction, Online learning etc.
Keras.io Cross- Python API for neural networks ,
platform supports CNN
Rapid Cross- Java Data loading & Transformation
Miner platform Data preprocessing &
visualization.
Oryx2 Cross Python collaborative filtering,
Platform classification, regression , DL,
CNN
73