Scribd
Upload
39 views28 pages

Lecture 2

This document provides an overview of artificial intelligence (AI). It discusses how AI aims to build rational agents that can perceive and act in their environment. The goal of AI is to build agents that can think and act rationally to maximize their goals. Deep learning using neural networks is a key technique in modern AI and has achieved success in areas like computer vision, natural language processing, and games. The document also provides a brief history of AI and discusses some applications like self-driving cars, virtual assistants, and medical diagnosis.

Uploaded by

Lenovo
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
39 views28 pages

Lecture 2

This document provides an overview of artificial intelligence (AI). It discusses how AI aims to build rational agents that can perceive and act in their environment. The goal of AI is to build agents that can think and act rationally to maximize their goals. Deep learning using neural networks is a key technique in modern AI and has achieved success in areas like computer vision, natural language processing, and games. The document also provides a brief history of AI and discusses some applications like self-driving cars, virtual assistants, and medical diagnosis.

Uploaded by

Lenovo
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 28

Artificial Intelligence

Lecture 2
What is AI?
The science of making machines that:

Think like people Think rationally

Act like people Act rationally


Acting rationally: rational agent
• Rational behavior: doing the right thing
• The right thing: that which is expected to
maximize goal achievement, given the
available information
Rational agents
• The goal of AI is to build
rational agents
• An agent is an entity that
perceives and acts
• An agent is a function from
percept histories to actions:
[f: P* A]

• For any given class of


environments and tasks, we
seek the agent (or class of
agents) with the best
performance
• e.g.: Room cleaner robot
Sensors

Environment
Deep
Learning/
Neural
Networks

Actuators
Deep Learning in Artificial Intelligence
A (Short) History of AI
• 1943 McCulloch & Pitts: Boolean circuit model of brain
• 1950 Turing's "Computing Machinery and Intelligence"
• 1956 Dartmouth meeting: "Artificial Intelligence" adopted
• 1950s Early AI programs, including Samuel's checkers
program, Newell & Simon's Logic Theorist,
Gelernter's Geometry Engine
• 1965 Robinson's complete algorithm for logical reasoning
• 1966—73 AI discovers computational complexity
Neural network research almost disappears
• 1969—79 Early development of knowledge-based systems
• 1980-- AI becomes an industry
• 1986-- Neural networks return to popularity
• 1987-- AI becomes a science
• 1995-- The emergence of intelligent agents
What is Data?
• the quantities, characters, or symbols on
which operations are performed by a
computer, which may be stored and
transmitted in the form of electrical signals
and recorded on magnetic, optical, or
mechanical recording media.
What is information?
• Information is organized or classified
data, which has some meaningful values
for the receiver.
What is MetaData?
• a set of data that describes and gives
information about other data.
State-of-art Artificial Intelligence
• Self-driving cars (As of 2020)
– Twenty-nine U.S. states have passed laws permitting
autonomous cars. In Europe, cities in Belgium, France,
Italy and the UK are planning to operate transport
systems for driverless cars, and Germany, the
Netherlands, and Spain have allowed testing robotic
cars in traffic.
– Numerous major companies have developed working
autonomous vehicles
including Mercedes-Benz, General
Motors, Continental Automotive
Systems, Uber, Tesla,Bosch, Nissan, Toyota, Audi, Volv
o, Vislab from University of Parma, Oxford
University and Waymo , etc.
Computer Vision: Object Recognition
• Image Classification: ImageNet Large Scale Visual Recognition
Challenge (ILSVRC)

Szegedy, C., Ioffe, S., Vanhoucke, V.


and Alemi, A.A., 2017, February.
Inception-v4, inception-resnet and
the impact of residual connections
on learning. In AAAI (Vol. 4, p. 12).
Computer Vision: Object Recognition
• Image Classification: ImageNet Large Scale Visual Recognition
Challenge (ILSVRC)

Find a cat

Szegedy, C., Ioffe, S., Vanhoucke, V.


and Alemi, A.A., 2017, February.
Inception-v4, inception-resnet and
the impact of residual connections
on learning. In AAAI (Vol. 4, p. 12).
Computer Vision: Object Detection and
Segmentation

He, K., Gkioxari, G.,


Dollár, P. and Girshick,
R., 2017, October. Mask
r-cnn. In Computer
Vision (ICCV), 2017 IEEE
International
Conference on (pp.
2980-2988). IEEE.
Computer Vision: Image Captioning
and Question Answering
Medical Image Diagnostic

Deep Neural networks


Perform Better Than
Dermatologist for skin
Cancer Detection

Esteva, A., Kuprel, B.,


Novoa, R.A., Ko, J.,
Swetter, S.M., Blau, H.M.
and Thrun, S., 2017.
Dermatologist-level
classification of skin
cancer with deep neural
networks. Nature, 542(76
39), p.115.
Medical Image Diagnostic

Deep Neural networks


Perform Better Than
Dermatologist for skin
Cancer Detection

Esteva, A., Kuprel, B.,


Novoa, R.A., Ko, J.,
Swetter, S.M., Blau, H.M.
and Thrun, S., 2017.
Dermatologist-level
classification of skin
cancer with deep neural
networks. Nature, 542(76
39), p.115.
Natural Language Processing: Machine
Translation
• Machine Translation

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones,


L., Gomez, A.N., Kaiser, Ł. and Polosukhin, I., 2017.
Attention is all you need. In Advances in Neural
Information Processing Systems (pp. 5998-6008).
Natural Language Processing: Speech
Recognition

Chiu, Chung-Cheng, et al. "State-of-the-art


speech recognition with
sequence-to-sequence models." arXiv
preprint arXiv:1712.01769 (2017).
Why AI?: Self Driving Cars
• In 2015, the US states
of Nevada, Florida,
California, Virginia,
Washington D.C. allowed
the testing of
autonomous cars on
public roads.
• In 2017 Audi stated that
its latest A8 would be
autonomous at up to
speeds of 60 km/h using
its "Audi AI"
Why AI?: Games
• It became the first Computer Go program to
beat a human professional player on a
full-sized 19×19 board. In March 2016, it
beat Lee Sedol in a five-game match.
Why AI?: Virtual Personal Assistant
• Siri, Google Now are intelligent digital personal assistants on
various platforms (iOS, Android, and Windows Mobile). In
short, they help find useful information when you ask for it
using your voice; you can say “Where’s the nearest Chinese
restaurant?”,
“What’s on my schedule today?”,
“Remind me to call Jerry at eight
o’clock,” and the assistant will
respond by finding information,
relaying information from your
phone, or sending commands to
other apps.
Why AI?
• Medical : Many Surgeons now use robot assistants in
microsurgery. E.g. HipNav
• Humaniod Robot like ASIMO was designed to operate
in real-world environments, with the ability to walk or
run on two feet at speeds of up to 6 kilometres per
hour (3.7 mph)
• Information Retrieval: Search engines like Google and
Yahoo uses AI for data retrieval
• Computer Vision: OCR, face recognition (biometric,
tracking)
Text Book and Course Material
• Textbook: S. Russell and P. Norvig Artificial
Intelligence: A Modern Approach Prentice Hall,
2003
Advanced Topics in AI: Syllabus
Imagination: Deep Generative Models
Perception: Deep Convolution
Neural Networks
Thinking: Deep NeuroSymbolic
Reasoning and Probabilistic
Decision Making

Language Processing: Deep


Recurrent Neural Network
Control: Deep
Reinforcement Learning

Figure Rational Agent

You might also like