Download as pdf or txt
Download as pdf or txt
You are on page 1of 27

Introduction to Machine Learning:

Applications
(Motivation)

Dr. Hikmat Ullah Khan

Assistant Professor
Department of Computer Science
COMSATS Institute of Information Technology,
Wah Cantt, Pakistan
Email: Hikmat.ullah@ciitwah.edu.pk

September 16, 2018 Dr. Hikmat Ullah Khan 1


September 16, 2018 Dr. Hikmat Ullah Khan 2
September 16, 2018 Dr. Hikmat Ullah Khan 3
September 16, 2018 Dr. Hikmat Ullah Khan 4
Why “Learn” ?

 Machine learning is programming computers to


optimize a performance criterion using example
data or past experience.
 There is no need to “learn” to calculate payroll
 Learning is used when:
 Human expertise does not exist (navigating on Mars),
 Humans are unable to explain their expertise (speech
recognition)
 Solution changes in time (routing on a computer
network)
 Solution needs to be adapted to particular cases (user
biometrics)

5
What is Machine Learning?
 Optimize a performance criterion using example
data or past experience.
 Role of Statistics: Inference from a sample
 Role of Computer science: Efficient algorithms to
 Solve the optimization problem
 Representing and evaluating the model for inference

6
Real vs Fake

9/16/2018 Dr. Hikmat Ullah Khan 7


Spam detction
 Spam Emails
 Spam Messages
 Spam Videos

 Spam Techniques

9/16/2018 Dr. Hikmat Ullah Khan 8


Google’s AlphaGo beat the world
master as a game called Go

September 16, 2018 Dr. Hikmat Ullah Khan 9


Weather Forecasting

September 16, 2018 Dr. Hikmat Ullah Khan 10


Self Driving

September 16, 2018 Dr. Hikmat Ullah Khan 11


Even More

September 16, 2018 Dr. Hikmat Ullah Khan 12


Facebook – Chat Bot Army

September 16, 2018 Dr. Hikmat Ullah Khan 13


Social Bot (Rise and Hazards)

September 16, 2018 Dr. Hikmat Ullah Khan 14


Google Machine’s Dream

September 16, 2018 Dr. Hikmat Ullah Khan 15


September 16, 2018 Dr. Hikmat Ullah Khan 16
Role of Machine Learning

Increasing potential
to support
business decisions End User
Decision
Making

Data Visualization Business


Analyst
Visualization Techniques

Machine Learning & Data Data


Analyst
Mining

Basic Data Analysis

Data Preprocessing
DBA
Data Sources

September 16, 2018 Dr. Hikmat Ullah Khan 17


Process: A Typical View from ML

Input Data Data Pre- Machine Post-


Processing Learnin Processing
g

Data integration Pattern discovery Result evaluation


Normalization Association & correlation Pattern interpretation
Feature selection Classification Outcome visualization
Clustering
Dimension reduction
Outlier analysis
…………

September 16, 2018 Dr. Hikmat Ullah Khan 18


Machine Learning: On What Data?
 Database-oriented data sets and applications
 Relational database, data warehouse, transactional database
 Advanced data sets and advanced applications
 Text Datasets
 Time-series data, temporal data,
 Sequence data (incl. bio-sequences)
 Graphs, social networks and multi-linked data
 Object-relational databases
 Heterogeneous databases
 Multimedia database
 The World-Wide Web
 Social Web
 BigData
September 16, 2018 Dr. Hikmat Ullah Khan 19
Dig into Advanced Applications
 Google’s DeepMind Lab
 A Deep and Advanced Analysis of Machine Learning
 https://deepmind.com/
 IBM Watson
 Do your Work Best with IBM WATSON
 https://www.ibm.com/watson/
 DeepLearning
 A comprehensive computation using Machine Learning
 http://deeplearning.net/
 Top 15 Deep Learning Software of 2017
 https://www.predictiveanalyticstoday.com/deep-
learning-software-libraries/

September 16, 2018 Dr. Hikmat Ullah Khan 20


Do you have any interest
 What is the source of Interest
 Motivation?
 Reason
 My Interest is PREDICTION (for instance)
Applications

 Predicting the Risk of Chronic Disease: A Framework


Based on Graph Theory and Social Network Analysis

 Every team deserves a second chance: an extended


study on predicting team performance.

 Predicting of Job Failure in Compute Cloud Based on


Online Extreme Learning Machine: A Comparative
Study.

 Predicting Patient Hospitalization after Emergency


Readmission

 Predicting computer proficiency in older adults.


Applications

 Predicting epileptic seizures from scalp EEG based on


attractor state analysis.

 Predicting long-term product ratings based on few


early ratings and user base analysis.

 Predicting user behavior in electronic markets based


on personality-mining in large online social networks -
A personality-based product recommender
framework.

 Use of freely available datasets and machine learning


methods in predicting deforestation.
Applications Areas
 Predicting academic success by using context variables
and probabilistic classification.

 Predicting the delay of issues with due dates in


software projects.

 Predicting the helpfulness of online reviews using a


scripts-enriched text regression model.

 Towards an ensemble based system for predicting the


number of software faults.
Applications Areas
 Predicting happiness: user interactions and sentiment
analysis in an online travel forum.

 A Machine Learning Approach for Tracking and


Predicting Student Performance in Degree Programs.

 On Predicting Election Results using Twitter and Linked


Open Data: The Case of the UK 2010 Election.

 Predicting international Facebook ties through cultural


homophily and other factors.

Applications Areas
 Predicting Student Satisfaction and Outcomes in Online
Courses Using Learning Activity Indicators.

 On the feasibility of predicting popular news at cold


start.

 A deep learning approach for predicting the quality of


online health expert question-answering services.

 How are you feeling?: A personalized methodology for


predicting mental states from temporally observable
physical and behavioral information.

You might also like