Machine Learning BY UZMA TUFAIL MCS : section (E) ROLL NO: 15177 1/31/2016.

Machine LearningMachine Learning

BY UZMA TUFAILMCS : section (E) ROLL NO: 15177

1/31/2016

1: What is Learning?1: What is Learning?

• Permanent change that occurs in behavior as a result of experience.

• For example, it is possible to learn to open a lock as

a result of trial and error; possible to learn how to use a word processor as a result of following particular instructions.

1/31/2016

1/31/2016

2: What is Learning?2: What is Learning?

Many different answers, depending on the field you’re considering and whom you ask– AI vs. psychology vs. education vs.

neurobiology vs. …

1/31/2016

Does Memorization = Does Memorization = Learning?Learning?

Test : Ali learns his mother’s face

Memorizes:

But will he recognize:

1/31/2016

Thus he can generalize beyond what he’s seen!

1/31/2016 6

What is Machine Learning?What is Machine Learning? Building machines that automatically learn from

experience The goal of machine learning is to build computer

systems that can learn from their experience and adapt to their environment.– Important research goal of artificial intelligence

Small sampling of applications:– Data mining programs that learn to detect fraudulent credit

card transactions.– Programs that learn to filter spam email– Autonomous vehicles that learn to drive on public highways

1/31/2016

Why Machine Learning?Why Machine Learning?(Relatively) new kind of capability for

computers– Data mining: extracting new information from

medical records, maintenance records, etc.– Self-customizing programs: Web browser that

learns what you like and seeks it out– Applications we can’t program by hand: E.g.

speech recognition, autonomous driving

1/31/2016

Why Machine Learning?Why Machine Learning?(cont’d)(cont’d)

Understanding human learning and teaching: – Mature mathematical models might lend insight

The time is right:– Recent progress in algorithms and theory– Enormous amounts of data and applications– Substantial computational power– Budding industry (e.g. Google)

1/31/2016

Machine Learning vs. Expert Machine Learning vs. Expert SystemsSystems

ES: Expertise extraction tedious; ML: Automatic

ES: Rules might not incorporate intuition, which might mask true reasons for answer– E.g. in medicine, the reasons given for

diagnosis x might not be the objectively correct ones, and the expert might be unconsciously picking up on other info

– ML: More “objective”

1/31/2016

Machine Learning vs. Expert Machine Learning vs. Expert Systems (cont’d)Systems (cont’d)

ES: Expertise might not be comprehensive, e.g. physician might not have seen some types of cases

ML: Automatic, objective, and data-driven– Though it is only as good as the available data

1/31/2016 Stephen Scott, Univ. of Nebraska 11

Three phases in machine Three phases in machine learning?learning?

1. Training:a training set of examples of correct behavior is analyzed and some representation of the newly learnt knowledge is stored. This is often some form of rules.

1/31/2016

Three phases in machine Three phases in machine learning?learning?

2. Validation:the rules are checked and, if necessary, additional training is given. Sometimes additional test data are used, but instead of using a human to validate the rules, some other automatic knowledge based component may be used. The role of tester is often called the critic.

1/31/2016

Three phases in machine Three phases in machine learning?learning?

3. Application:the rules are used in responding to some new situations.

1/31/2016

Other Applications of MLOther Applications of ML The Google search engine uses numerous machine

learning techniques– Spelling corrector: “spehl korector”, “phonitick spewling”,

“Brytney Spears”, “Brithney Spears”, …– Grouping together top news stories from numerous sources (

news.google.com)– Analyzing data from over 3 billion web pages to improve

search results– Analyzing which search results are most often followed, i.e.

which results are most relevant

1/31/2016

Other Applications of ML Other Applications of ML (cont’d)(cont’d)

ALVINN, developed at CMU, drives autonomously on highways at 70 mph– Sensor input only a single, forward-facing camera

1/31/2016

Other Applications of ML Other Applications of ML (cont’d)(cont’d)

SpamAssassin for filtering spam e-mail Data mining programs for:

– Analyzing credit card transactions for anomalies– Analyzing medical records to automate diagnoses

Intrusion detection for computer security Speech recognition, face recognition Biological sequence analysis Each application has its own representation for features,

learning algorithm, hypothesis type, etc.

1/31/2016

ConclusionsConclusionsML started as a field that was mainly for

research purposes, with a few niche applications

Now applications are very widespreadML is able to automatically find patterns in

data that humans cannotHowever, still very far from emulating

human intelligence!– Each artificial learner is task-specific