Course OverviewWhat is AI?

What are the Major Challenges?

What are the Main Techniques?

Where are we failing, and why?

Step back and look at the Science

Step back and look at the History of AI

What are the Major Schools of Thought?

What of the Future?

Done

Done

Course Overview What is AI?

What are the Major Challenges?

What are the Main Techniques? (How do we do it?)

Where are we failing, and why?

Step back and look at the Science

Step back and look at the History of AI

What are the Major Schools of Thought?

What of the Future?

Course Overview What is AI?

What are the Major Challenges?

What are the Main Techniques? (How do we do it?)

Where are we failing, and why?

Step back and look at the Science

Step back and look at the History of AI

What are the Major Schools of Thought?

What of the Future?

Search Logics (knowledge representation and reasoning) Planning Bayesian belief networks Neural networks Evolutionary computation Reinforcement learning

Course Overview What is AI?

What are the Major Challenges?

What are the Main Techniques? (How do we do it?)

Where are we failing, and why?

Step back and look at the Science

Step back and look at the History of AI

What are the Major Schools of Thought?

What of the Future?

Search Logics (knowledge representation and reasoning) Planning Bayesian belief networks Neural networks Evolutionary computation Reinforcement learning

Course Overview What is AI?

What are the Major Challenges?

What are the Main Techniques? (How do we do it?)

Where are we failing, and why?

Step back and look at the Science

Step back and look at the History of AI

What are the Major Schools of Thought?

What of the Future?

Search Logics (knowledge representation and reasoning) Planning Bayesian belief networks Neural networks Evolutionary computation Reinforcement learning

These are all in fact types of

“Machine Learning”

Dealing with Uncertainty The need to deal with uncertainty arose in “expert systems”

Code expertise into a computer systemExample: Medical diagnosis: MYCIN Equipment failure diagnosis in a factory

Sample from MYCIN: IF

The infection is primary-bacteremia AND The site of the culture is one of the sterile sites AND The suspected portal of entry is the gastrointestinal tract

THEN There is suggestive evidence (70%) that the infection is bacteroid

Expert systems often have long chains IF X THEN Y … IF Y THEN Z … IF Z THEN W … If uncertainty is not handled correctly, errors build up, wrong diagnosis Also, there may be dependencies, e.g. X and Y depend on each other Leads to more errors…

Need a proper way to deal with uncertainty

How do Humans Deal with Uncertainty? Not very well…

Consider a form of cancer which afflicts 0.8% of people (rare) A lab has a test to detect the cancer The test has a 98% chance to give an accurate result Mr. Bloggs goes for the test

The result comes back positive i.e. the test says he has cancer

What is the chance that he has the cancer? 28%

Afflicts experts too Studies have shown: human experts thinking of likelihoods do not reason

like mathematical probability

A

B C

D E

Increased total serum count

Metastatic cancer

Brain Tumour

Severe headachesComa

A

B C

D E

Increased total serum count

Metastatic cancer

Brain Tumour

Severe headachesComa

No Link

A

B C

D E

Increased total serum count

Metastatic cancer

Brain Tumour

Severe headachesComa

Serum count

Brain tumour

Coma

Yes Yes 95%

Yes No 94%

No Yes 29%

No No 0.1%

A

B C

D E

Increased total serum count

Metastatic cancer

Brain Tumour

Severe headachesComa

Serum count

Brain tumour

Coma

Yes Yes 95%

Yes No 94%

No Yes 29%

No No 0.1%

Brain tumour

headache

Yes 70%

No 1%

A

B C

D E

Increased total serum count

Metastatic cancer

Brain Tumour

Severe headachesComa

Serum count

Brain tumour

Coma

Yes Yes 95%

Yes No 94%

No Yes 29%

No No 0.1%

Brain tumour

headache

Yes 70%

No 1%

… …

… …

… …

… …

… …

… …

… …

… …

… …

Inference in Belief Networks Questions for a belief network:

Diagnosis Work backwards from some evidence to a hypothesis

Causality Work forwards from some hypothesis to likely evidence Test a hypothesis, find likely symptoms

In general – mixed mode Give values for some evidence variables Ask about values of others

No other approach handles all these modes

Reasoning can take some time Need to be careful to design network Local structure: few connections

How Good are Belief Networks? Relieves you from coding all possible dependencies

How many possibilities if full network?

Tools are available Build network graphically System handles mathematical probabilities

Case study: Pathfinder a medical expert system

Assists pathologists with diagnosis of lymph-node diseases Pathfinder is a pun

User enters initial findings Pathfinder lists possible diseases User can

Enter more findings Ask pathfinder which findings would narrow possibilities

Pathfinder refines the diagnosis Pathfinder version based on Belief Networks performs significantly better

than human pathologists

QUIZ

“Machines will be capable,

within _____ years,

of doing any work that a man can do.”

Herbert Simon, 1965.

What disciplines are considered as sub-areas of Cognitive Science?

1966: “Any task that requires real understanding of natural language is

too difficult for a computer” - Bar-Hillel

Time flies like an arrow.

Give an example which shows why speech recognition is hard for computers.

Major tasks in robotics:

1. Localisation/mapping Range finders Landmarks Always uncertainty

2. ?

DARPA Grand Challenge 2004

150-mile route in Mojave Desert (off-road course)

Best performance? (require accuracy to nearest 2 miles)

Vision Hierarchy

4. High level Models

3. Mid level ????

2. Putting together Multiple images

1. Low level processing on a single image

0. The physics of image formation

Go (Wei Qi)Humans don’t want to play computers because ?

John McCarthy, "Programs with Common

Sense", 1958.

"Our ultimate objective is to make "Our ultimate objective is to make programs that learn from their programs that learn from their

experience as effectively as humans experience as effectively as humans do. We shall…say that a program do. We shall…say that a program

has common sense if ?”has common sense if ?”

DefenceA big user of AI.

"... the deployment of a single ??????

called DART during the Desert Shield/Storm Campaign paid back all US government investment in AI/KBS research over a 30 year

period."

Tate A. Smart Planning. ARPI Proc. 1996.

Can use logic to represent a hierarchy of concepts isa(Tweety, canary) isa(canary, bird) isa(bird, animal) isa(animal, living_thing) isa(living_thing, physical_thing) isa(physical_thing, tangible_thing) isa(tangible_thing, thing)

What do we call this?

“Machines will be capable,

within _____ years,

of doing any work that a man can do.”

Herbert Simon, 1965.

“Machines will be capable,

within twenty years,

of doing any work that a man can do.”

Herbert Simon, 1965.

What disciplines are considered as sub-areas of Cognitive Science?

What disciplines are considered as sub-areas of Cognitive Science?

Cognitive Science

Psychology

Philosophy

Neuroscience

Artificial Intelligence

Linguistics

Anthropology

1966: “Any task that requires real understanding of natural language is

too difficult for a computer” - Bar-Hillel

1966: “Any task that requires real understanding of natural language is

too difficult for a computer” - Bar-Hillel

Time flies like an arrow.

Time flies like an arrow.

(You should) time flies as you would (time) an arrow

Time flies in the same way that an arrow would (time them)

Time those flies that are like arrows

Fruit flies like a banana

each of above

Time magazine travels straight when thrown

Give an example which shows why speech recognition is hard for computers.

Give an example which shows why speech recognition is hard for computers.

“eat I scream” vs. “eat ice cream”

Major tasks in robotics:

1. Localisation/mapping Range finders Landmarks Always uncertainty

2. ?

Major tasks in robotics:

1. Localisation/mapping Range finders Landmarks Always uncertainty

2. Motion planning For body location in world For arms/fingers

DARPA Grand Challenge 2004

150-mile route in Mojave Desert (off-road course)

Best performance? (require accuracy to nearest 2 miles)

DARPA Grand Challenge 2004

150-mile route in Mojave Desert (off-road course)

Best performance: 7.36 miles

Vision Hierarchy

4. High level Models

3. Mid level ????

2. Putting together Multiple images

1. Low level processing on a single image

0. The physics of image formation

Vision Hierarchy

4. High level Models

3. Mid level Segmentation

2. Putting together Multiple images

1. Low level processing on a single image

0. The physics of image formation

Go (Wei Qi)Humans don’t want to play computers because ?

Go (Wei Qi)Humans don’t want to play computers because computers are too bad

John McCarthy, "Programs with Common

Sense", 1958.

"Our ultimate objective is to make "Our ultimate objective is to make programs that learn from their programs that learn from their

experience as effectively as humans experience as effectively as humans do. We shall…say that a program do. We shall…say that a program

has common sense if ?”has common sense if ?”

John McCarthy, "Programs with Common

Sense", 1958.

"Our ultimate objective is to make "Our ultimate objective is to make programs that learn from their programs that learn from their

experience as effectively as humans experience as effectively as humans do. We shall…say that a program do. We shall…say that a program

has common sense if it has common sense if it automatically deduces for itself a automatically deduces for itself a sufficient wide class of immediate sufficient wide class of immediate consequences of anything it is told consequences of anything it is told

and what it already knows.”and what it already knows.”

DefenceA big user of AI.

"... the deployment of a single ??????

called DART during the Desert Shield/Storm Campaign paid back all US government investment in AI/KBS research over a 30 year

period."

Tate A. Smart Planning. ARPI Proc. 1996.

DefenceA big user of AI.

"... the deployment of a single logistics support aid called DART during the Desert Shield/Storm

Campaign paid back all US government investment in AI/KBS research over a 30 year period."

Tate A. Smart Planning. ARPI Proc. 1996.

Can use logic to represent a hierarchy of concepts isa(Tweety, canary) isa(canary, bird) isa(bird, animal) isa(animal, living_thing) isa(living_thing, physical_thing) isa(physical_thing, tangible_thing) isa(tangible_thing, thing)

What do we call this?

Can use logic to represent a hierarchy of concepts isa(Tweety, canary) isa(canary, bird) isa(bird, animal) isa(animal, living_thing) isa(living_thing, physical_thing) isa(physical_thing, tangible_thing) isa(tangible_thing, thing)

What do we call this? Ontology