Scribd
Upload
2 views

Lecture 1

The document outlines an introductory lecture on Artificial Intelligence (AI) by Engr. Hira Khalid, covering key paradigms such as supervised classification, regression, and clustering, along with their applications in various fields like spam detection and image classification. It also highlights the historical milestones in AI development from the 1950s to the present, emphasizing significant breakthroughs and the evolution of machine learning. The course aims to provide a comprehensive understanding of AI mechanisms and their practical uses without requiring a textbook.

Uploaded by

yusrajaved56
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
2 views

Lecture 1

The document outlines an introductory lecture on Artificial Intelligence (AI) by Engr. Hira Khalid, covering key paradigms such as supervised classification, regression, and clustering, along with their applications in various fields like spam detection and image classification. It also highlights the historical milestones in AI development from the 1950s to the present, emphasizing significant breakthroughs and the evolution of machine learning. The course aims to provide a comprehensive understanding of AI mechanisms and their practical uses without requiring a textbook.

Uploaded by

yusrajaved56
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 21

Artificial Intelligence

Lecture 1
Engr. Hira Khalid
Artificial Intelligence
Image Classification

Document Categorization

Speech Recognition Protein Classification Spam Detection

Branch Prediction Fraud Detection Natural Language Processing

Playing Games Computational Advertising

2
Artificial Intelligence is Changing the
World
“Machine learning is the hot new thing”
(John Hennessy, President, Stanford)

“A breakthrough in machine learning would be worth


ten
Microsofts” (Bill Gates, Microsoft)

“Web rankings today are mostly a matter of machine learning”


(Prabhakar Raghavan, VP Engineering at Google)
The COOLEST TOPIC IN SCIENCE
• “A breakthrough in machine learning would be
worth ten Microsofts” (Bill Gates, Chairman,
Microsoft)
• “Machine learning is the next Internet”
(Tony Tether, Director, DARPA)
• Machine learning is the hot new thing”
(John Hennessy, President, Stanford)
• “Web rankings today are mostly a matter of machine
learning”
(Prabhakar Raghavan, Dir. Research, Yahoo)
• “Machine learning is going to result in a real
revolution”
(Greg Papadopoulos, CTO, Sun)
• “Machine learning is today’s discontinuity”
(Jerry Yang, CEO, Yahoo)
This course: introduction to Artificial
Intelligence.
• Cover (some of) the most commonly used artificial
intelligence paradigms and algorithms.
• Sufficient amount of details on their mechanisms:
explain why they work, not only how to use them.

• Applications.
What is Artificial Intelligence?
Examples of important artificial intelligence
paradigms.
Supervised Classification

from data to discrete classes


Supervised Classification. Example: Spam Detection
Decide which emails are spam and which are important.
Supervised
Not spam classification
spam

Goal: use emails seen so far to produce good prediction rule for
future data.
Supervised Classification. Example: Spam Detection
Represent each message by features. (e.g., keywords, spelling,
etc.)

exampl labe
e l

Reasonable RULES:
+ + -
Predict SPAM if unknown AND (money OR pills) + -
+
Predict SPAM if 2money + 3pills –5 known > 0
-
-- -

Linearly separable
Supervised Classification. Example: Image classification

•Handwritten digit
recognition (convert hand-
written digits to characters 0..9)

• Face Detection and Recognition


Supervised Classification. Many other examples
• Weather prediction

• Medicine:
– diagnose a disease
• input: from symptoms, lab measurements, test results, DNA tests,
…
• output: one of set of possible diseases, or “none of the above”
• examples: audiology, thyroid cancer, diabetes, …
– or: response to chemo drug X
– or: will patient be re-admitted soon?

• Computational Economics:
– predict if a stock will rise or fall
– predict if a user will click on an ad or not
• in order to decide which ad to show
Regression. Predicting a numeric value

Stock market

Weather prediction

Temperature
72° F

Predict the temperature at any given location


Other AI Paradigm
Clustering: discovering structure in data (only unlabeled data)
• E.g, cluster users of social networks by interest (community detection).
Faceboo Twitter
k Network
network

Semi-Supervised Learning: learning with labeled & unlabeled data

Active Learning: learns pick informative examples to be labeled

Reinforcement Learning (acommodates indirect or delayed feedback)

Dimensionality Reduction

Collaborative Filtering (Matrix Completion), …


Many communities relate to AI
Agents in Artificial Intelligence
History of Artificial Intelligence
Early AI Foundations (1950-1970)

1950 - Turing Proposes Text:


Alan Turing, a British mathematician, proposed the Turing Test, a method to
determine whether a machine can exhibit intelligent behavior similar to a human.
This laid the foundation for AI.
1956 - Term "AI" Coined:
John McCarthy introduced the term Artificial Intelligence (AI) at the Dartmouth
Conference, marking the official beginning of AI as a field of study.
1965 - ELIZA Chatbot:
Joseph Weizenbaum developed ELIZA, one of the first chatbots, capable of
mimicking human-like conversation by pattern-matching text input.
1969 - Perceptrons Criticized:
Marvin Minsky and Seymour Papert criticized perceptrons (early neural networks)
in their book, causing a decline in AI research for years.
1970 - First AI Conference:
The first AI conference was held to bring together researchers working in the AI
field.
AI Progress in the Late 20th Century (1979-1999)

•1979 - Japan’s AI Project:


Japan launched an ambitious Fifth Generation Computer Systems (FGCS)
project to advance AI research.
•1985 - Natural Language Processing (NLP):
AI started making progress in understanding and generating human
language, a major step in Natural Language Processing (NLP).
•1997 - Deep Blue Victory:
IBM’s Deep Blue defeated world chess champion Garry Kasparov,
demonstrating the power of AI in strategic decision-making.
•1999 - RoboCup Starts:
The RoboCup (Robot Soccer World Cup) was introduced to promote AI and
robotics research.
AI in the 21st Century (2005-2021)
2005 - Standard AI:
AI became widely used in various industries, such as automation, gaming, and expert systems.
2009 - DeepMind Founded:
DeepMind, an AI research company (later acquired by Google), was established, leading to major breakthroughs
in AI.
2011 - Watson Wins Jeopardy:
IBM’s Watson AI defeated human champions in the quiz show Jeopardy!, showing AI’s ability to process vast
amounts of data quickly.
2012 - Cat Video Breakthrough:
AI trained on deep learning successfully recognized cat images from YouTube videos, a milestone for neural
networks.
2016 - AlphaGo:
DeepMind’s AlphaGo defeated the world champion in the board game Go, demonstrating AI's ability to learn
complex strategies.
2018 - GPT Model Released:
OpenAI introduced the GPT (Generative Pre-trained Transformer) model, significantly improving AI’s ability to
understand and generate human-like text.
2020 - GPT-3 Launch:
GPT-3, an advanced language model, was released, capable of writing essays, generating code, and performing
complex tasks.
2021 - AI Advancement:
AI continued to evolve, improving in fields like computer vision, robotics, healthcare, and automation.
Source Materials
No textbook required. Will point to slides and freely
available online material.
Useful textbooks:
Machine Learning, Tom Mitchell, McGraw Hill, 1997.

Machine Learning: a Probabilistic Perspective,


K. Murphy, MIT Press, 2012

Pattern Recognition and Machine Learning


Christopher Bishop, Springer-Verlag 2006

You might also like