Advanced Artificial Intelligence

(高 级 人 工 智 能)

Artificial Intelligence 9/18/18

 Advanced Artificial Intelligence
#L1
Introduction

Yuan Caixia (袁 彩霞)

[email protected]
Center for Intelligence Science and Technology,
School of Computer Science

Artificial Intelligence 9/18/18

• More about me:
– From 2009 –
• Asso. Professor, Beijing University of Posts and
Telecommunications (BUPT)
– From 2007-2009
• Received Ph.D degree in the University of Tokushima, Japan
• Intelligence Science and System
– From 2003-2007
• Received Ph.D degree in BUPT
• Computer Science and Technology
– Current research interest: natural language processing,
dialogue system, machine learning and its
applications in large scale text mining

Artificial Intelligence 9/18/18

 Topics for Today

• What is Artificial Intelligence (AI)?

• Why do we study AI?
• A rather simple sketch of AI history
• Key concepts
• Course Plan and Administrivia
• Recommended Textbooks

Artificial Intelligence 9/18/18

 A Few Quotes
• “The development of full artificial intelligence could spell the end of
the human race… Humans, who are limited by slow biological
evolution, couldn't compete, and would be superseded.”— Stephen
Hawking
• “I mean with artificial intelligence we’re summoning the demon.” —
Elon Musk
• “A year spent in artificial intelligence is enough to make one believe
in God.” —Alan Perlis
• “There is no reason and no way that a human mind can keep up
with an artificial intelligence machine by 2035.” —Gray Scott
• “Artificial intelligence would be the ultimate version of Google.” —
Larry Page
• “I visualize a time when we will be to robots what dogs are to
humans, and I’m rooting for the machines.” —Claude Shannon

Artificial Intelligence 9/18/18

 So What Is Artificial Intelligence?

A branch of Computer Science.

Examines how we can achieve intelligent

behavior through computation.

Artificial Intelligence 9/18/18

 What is intelligence?

Are these Intelligent?

Artificial Intelligence 9/18/18
 What is intelligence?

Are these Intelligent?

Artificial Intelligence 9/18/18
 What is intelligence?

Are these Intelligent?

Artificial Intelligence 9/18/18
 What is Intelligence?

• Webster says:
– The capacity to acquire and apply knowledge.
– The faculty of thought and reason.
–…
• What features/abilities do humans
(animals/animate objects) have that you think
are indicative or characteristic of intelligence?
– Abstract concepts, mathematics, language,
problem solving, memory, logical reasoning,
planning ahead, emotions, morality, ability to
learn/adapt, etc…

Artificial Intelligence 9/18/18

 Artificial Intelligence

• Studies how to achieve intelligent behavior

through computational means.
• This makes AI a branch of Computer Science.
• Why do we think that intelligence can be
captured through computation?
– Modeling the processing that our brains do as
computation has proved to be successful.
– Hence, human intelligence can arguably be best
modeled as a computational process.

Artificial Intelligence 9/18/18

 Classical Test of (Human) Intelligence

• The Turing Test:

– A human interrogator. Communicates
with a hidden subject that is either a
computer system or a human.
– If the human interrogator cannot reliably
decide whether or not the subject is a
computer, the computer is said to have
passed the Turing test.

• Weak Turing type tests:

Artificial Intelligence 9/18/18

 Human Intelligence

• Turing provided some very persuasive

arguments that a system passing the Turing
test is intelligent.
– We can only really say it behaves like a human
– Nothing guarantees that it thinks like a human

• The Turing test does not provide much

traction on the question of how to actually
build an intelligent system.

Artificial Intelligence 9/18/18

 Human Intelligence

• Recently some claims have been made of AI

systems that can pass the Turing Test.
• However, these systems operate on
subterfuge, and were able to convince a
rather naïve jury that they were human like.
• The main technique used is obfuscation …
rather than answering questions the system
changed the topic!
• This is not what Turing described in his Turing
Test.

Artificial Intelligence 9/18/18

 Human Intelligence

• But more importantly, we know very little

about how the human brain performs its
higher level processes.
• Hence, this point of view provides very little
information from which a scientific
understanding of these processes can be built.
• Nevertheless, neuroscience has been very
influential in some areas of AI. For example, in
robotic sensing, vision processing, etc.

Artificial Intelligence 9/18/18

 Human Intelligence

• Although computers and humans have a very different

architecture with quite different abilities, the modern
computer hardware is approaching to a level as high as
that of human beings.

Computer Human Brain

Computational units 8 CPUs, 1010 gates 1011 neurons
Storage units 1010 bits RAM 1011 neurons
1013 bits disk 1014 synapses
Cycle time 10-9 sec 10-3 sec
Bandwith 1010 bits/sec 1014 bits/sec
Memory updates/sec 1010 1014

Artificial Intelligence 9/18/18

 Computational Intelligence

• AI tries to understand and model intelligence as a

computational process.
• Thus we try to construct systems whose
computation achieves or approximates the
desired notion of reasoning, thinking and
learning.
• Hence AI is part of Computer Science.
– Other areas interested in the study of intelligence lie
in other areas or study, e.g., cognitive science which
focuses on human intelligence. Such areas are very
related, but their central focus tends to be different.

Artificial Intelligence 9/18/18

 Computational Intelligence

• General-purpose AI like the robots of science

fiction is incredibly hard
– Human brain appears to have lots of special and
general functions, integrated in some amazing
way that we really do not understand at all (yet)
• Special-purpose AI is more doable (nontrivial)
– E.g., chess/poker playing programs, logistics
planning, automated translation, voice
recognition, web search, data mining, medical
diagnosis, keeping a car on the road, … … … …

Artificial Intelligence 9/18/18

 Subareas of AI

• Reasoning and decision making

– Knowledge representation
– Reasoning (logical, probabilistic)
– Decision making (search, planning, decision
theory)
• Machine Learning, Neural networks OUR FOCUS
• Robotics
• Perception: vision, speech understanding, etc.
• Natural language processing

Artificial Intelligence 9/18/18

 Subareas of AI

• Nor will we discuss Computer Vision nor Natural

Language to any significant extent.
– All of these areas have developed a number of
specialized theories and methods specific to the
problems they study.
• The topics we will study here are fundamental
techniques used in various AI systems, and often
appear in advanced research in many other sub-
areas of AI.
• In short, what we cover here is not sufficient for a
deep understanding of AI, but it is a good start.

Artificial Intelligence 9/18/18

 A Brief History of AI

• 50s/60s: Early successes! AI can draw logical conclusions,

prove some theorems, create simple plans… Some initial
work on neural networks…
• Led to overhyping: researchers promised funding
agencies spectacular progress, but started running into
difficulties:
– Ambiguity: highly funded translation programs (Russian to English)
were good at syntactic manipulation but bad at disambiguation
• “The spirit is willing but the flesh is weak” becomes “The vodka is good
but the meat is rotten”
– Scalability/complexity: early examples were very small, programs could
not scale to bigger instances
– Limitations of representations used

Artificial Intelligence 9/18/18

 A Brief History of AI

• 70s, 80s: Creation of expert systems (systems

specialized for one particular task based on
experts’ knowledge), wide industry adoption
• Again, overpromising…
• … led to AI winter(s)
– Funding cutbacks, bad reputation

Artificial Intelligence 9/18/18

 A Brief History of AI

• More rigorous, scientific, formal/mathematical

• Fewer grandiose promises
• Divided into many subareas interested in particular
aspects
• More directly connected to “neighboring” disciplines
– Theoretical computer science, statistics, economics,
operations research, biology, psychology/neuroscience, …
– Often leads to question “Is this really AI”?
• Some senior AI researchers are calling for re-
integration of all these topics, return to more
grandiose goals of AI

Artificial Intelligence 9/18/18

 AI Successes
• Games: chess, checkers, poker, bridge, backgammon…
– Search
• Physical skills: driving a car, flying a plane or helicopter,
vacuuming...
– Sensing, machine learning, planning, search, probabilistic
reasoning
• Language: machine translation, speech recognition,
character recognition, …
– Knowledge representation, machine learning, probabilistic
reasoning
• Vision: face recognition, face detection, digital photographic
processing, motion tracking, …
• Commerce and industry: page rank for searching, fraud
detection, trading on financial markets…
– Search, machine learning, probabilistic reasoning

Artificial Intelligence 9/18/18

 What We Cover in This Course
• Tentative Topics:
– Linear Models: 2 units
– Neural Networks: From Shallow To Deep: 2 units
– Convolutional Neural Network: 2 units
– Unsupervised Feature Learning: 2 units
– Recurrent Networks: 2 units
– Reinforcement Learning: 3 units
– Readings: 1 unit

Artificial Intelligence 9/18/18

 How You Will be Graded

• Course work:
– 1. Two assignments (mainly programming): 60% in
total equally divided.
– 2. A final research report (no less than 4 pages) worth
40%
• Please note. Late assignments will not be
accepted. You will get zero for anything past the
due date
• All assignments are to be done individually.
• You can discuss the assignments with other
students, but you should not give your code (or
parts of your code) to other students.

Artificial Intelligence 9/18/18

 Reference Materials

• Recommended Textbook:
– Stuart Russell and Peter Norvig. Artificial Intelligence: A Modern
Approach. 3rd Edition. Prentice Hall, 2009. – elementary and
interesting
– Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning. MIT
Press. http://www.deeplearningbook.org/, 2016. -- heavy but
charming
– T. Mitchell. Machine Learning. McGraw Hill, 1997. (Chinese ed., 2003).
-- old but classical
– Hastie, Tibshirani and Friedman. The Elements of Statistical Learning:
Data Mining, Inference, and Prediction, Springer, 2009. -- difficult but
essential
– Christopher M. Bishop. Pattern Recognition and Machine Learning.
Springer, 2006. -- heavy but charming
• Recommended but not required.

Artificial Intelligence 9/18/18

 Reference Materials
• A portion of slides are borrowed from
– Michael I. Jordan, UC Berkeley at
http://www.cs.berkeley.edu/~jordan/courses/
– Andrew W. Moore, CMU at
http://www.cs.cmu.edu/~awm/tutorials
– Yoshua Bengio, U. Montreal at
https://ift6266h16.wordpress.com/
– Ng. Andrew, Stanford University at
http://www.stanford.edu/class/cs229/
– Feifei-Li, Stanford University at
http://cs231n.stanford.edu/syllabus.html
– ...
– And many of the figures are provided by Chris Bishop’s textbook: ”Pattern Recognition and
Machine Learning”
• Open courses
– Machine Learning
– Neural Networks for Machine Learning
– deaplearning.ai
– …

Artificial Intelligence 9/18/18

 Useful resources & links
• Conferences:
– International Conference on Machine Learning (ICML)
– Neural Information Processing Systems Conference (NIPS)
– Annual Conference on Learning Theory(COLT)
– Association for the Advancement of Artificial Intelligence (AAAI)
– International Joint Conferences on Artificial Intelligence (IJCAI)
– ICLR ( International Conference on Learning Representations)
– International Conference on Data Mining (ICDM)
– ACM SIGIR
– ACM SIGKDD
– ACM CIKM
– Association for Computational Linguistics (ACL)
– IEEE Conference on Computer Vision and Pattern Recognition
– ...
• Journals:
– Machine Learning Journal
– Journal of Machine Learning Research
– Artificial Intelligence Journals
– ACM Transactions on Knowledge Discovery from Data
– Data Mining and Knowledge Discovery
– IEEE-Transactions on Pattern Analysis and Machine Intelligence
– Neural Computation
– IEEE-Transactions on Neural Networks and Learning Systems

Artificial Intelligence 9/18/18

• How to contact us:
Please email [email protected] for all
questions related to lectures, homeworks, and
projects.
• You can also get the lecture slides by visiting
[email protected] (PW: yuancaixia)

• Next lecture: Basic Mathematics Review

Artificial Intelligence 9/18/18

 Thank you!

Artificial Intelligence 9/18/18