Artificial Intelligence: A Modern Approach, 4th Edition
SOLUTION MANUAL:
EXERCISE SOLUTIONS
FOR ARTIFICIAL
INTELLIGENCE A
MODERN APPROACH
FOURTH EDITION
STUART J. RUSSELL
AND PETER NORVIG
Solution Manual Page
, Artificial Intelligence: A Modern Approach, 4th Edition
1.1
a. Dictionary Definitions Of Intelligence Talk About ―The Capacity To Acquire
And Apply Knowledge‖ Or ―The Faculty Of Thought And Reason‖ Or ―The
Ability To Comprehend And Profit From Experience.‖ These Are All Reasonable
Answers, But If We Want Something Quantifiable We Would Use Something
Like ―The Ability To Apply Knowledge In Order To Perform Better In An
Environment.‖
b. We Define Artificial Intelligence As The Study And Construction Of Agent
Programs That Perform Well In A Given Environment, For A Given Agent
Architecture.
c. We Define An Agent As An Entity That Takes Action In Response To Percepts
From An Envi- Ronment.
1.2 See The Solution For Exercise 26.1 For Some Discussion Of Potential Objections.
The Probability Of Fooling An Interrogator Depends On Just How Unskilled
The Interroga- Tor Is. One Entrant In The 2002 Loebner Prize Competition (Which Is
Not Quite A Real Turing Test) Did Fool One Judge, Although If You Look At The
Transcript, It Is Hard To Imagine What That Judge Was Thinking. There Certainly
Have Been Examples Of A Chatbot Or Other Online Agent Fooling Humans. For
Example, See See Lenny Foner’s Account Of The Julia Chatbot At
Foner.Www.Media.Mit.Edu/People/Foner/Julia/. We’d Say The Chance Today Is
Something Like 10%, With The Variation Depending More On The Skill Of The
Interrogator Rather Than The Program. In 50 Years, We Expect That The
Entertainment Industry (Movies, Video Games, Com- Mercials) Will Have Made
Sufficient Investments In Artificial Actors To Create Very Credible Impersonators.
1.3 The 2002 Loebner Prize (Www.Loebner.Net) Went To Kevin Copple’s Program
ELLA. It Consists Of A Prioritized Set Of Pattern/Action Rules: If It Sees A Text String
Matching A Certain Pattern, It Outputs The Corresponding Response, Which May
Include Pieces Of The Current Or Past Input. It Also Has A Large Database Of Text
And Has The Wordnet Online Dictionary. It Is Therefore Using Rather Rudimentary
Tools, And Is Not Advancing The Theory Of AI. It Is Provid-
Solution Manual Page
, Artificial Intelligence: A Modern Approach, 4th Edition
Ing Evidence On The Number And Type Of Rules That Are Sufficient For Producing
One Type Of Conversation.
1.4 No. It Means That AI Systems Should Avoid Trying To Solve Intractable
Problems. Usually, This Means They Can Only Approximate Optimal Behavior. Notice
That Humans Don’t Solve NP- Complete Problems Either. Sometimes They Are Good
At Solving Specific Instances With A Lot Of
Structure, Perhaps With The Aid Of Background Knowledge. AI Systems Should
Attempt To Do The Same.
1.5 No. IQ Test Scores Correlate Well With Certain Other Measures, Such As
Success In College, But Only If They’re Measuring Fairly Normal Humans. The IQ Test
Doesn’t Measure Everything. A Program That Is Specialized Only For IQ Tests (And
Specialized Further Only For The Analogy Part) Would Very Likely Perform Poorly
On Other Measures Of Intelligence. See The Mismea- Sure Of Man By Stephen Jay
Gould, Norton, 1981 Or Multiple Intelligences: The Theory In Practice By Howard
Gardner, Basic Books, 1993 For More On IQ Tests, What They Measure, And What
Other Aspects There Are To ―Intelligence.‖
1.6 Just As You Are Unaware Of All The Steps That Go Into Making Your Heart
Beat, You Are Also Unaware Of Most Of What Happens In Your Thoughts. You Do
Have A Conscious Awareness Of Some Of Your Thought Processes, But The
Majority Remains Opaque To Your Consciousness. The Field Of Psychoanalysis Is
Based On The Idea That One Needs Trained Professional Help To Analyze One’s
Own Thoughts.
1.7
a. (Ping-Pong) A Reasonable Level Of Proficiency Was Achieved By Andersson’s
Robot (An- Dersson, 1988).
b. (Driving In Cairo) No. Although There Has Been A Lot Of Progress In
Automated Driving, All Such Systems Currently Rely On Certain Relatively
Constant Clues: That The Road Has Shoulders And A Center Line, That The Car
Ahead Will Travel A Predictable Course, That Cars Will Keep To Their Side Of
Solution Manual Page
, Artificial Intelligence: A Modern Approach, 4th Edition
The Road, And So On. To Our Knowledge, None Are Able To Avoid Obstacles
Or Other Cars Or To Change Lanes As Appropriate; Their Skills Are Mostly
Confined To Staying In One Lane At Constant Speed. Driving In Downtown
Cairo Is Too Unpredictable For Any Of These To Work.
c. (Shopping At The Market) No. No Robot Can Currently Put Together The Tasks
Of Moving In A Crowded Environment, Using Vision To Identify A Wide Variety
Of Objects, And Grasping The Objects (Including Squishable Vegetables)
Without Damaging Them. The Component Pieces Are Nearly Able To Handle
The Individual Tasks, But It Would Take A Major Integra- Tion Effort To Put It
All Together.
Solution Manual Page
SOLUTION MANUAL:
EXERCISE SOLUTIONS
FOR ARTIFICIAL
INTELLIGENCE A
MODERN APPROACH
FOURTH EDITION
STUART J. RUSSELL
AND PETER NORVIG
Solution Manual Page
, Artificial Intelligence: A Modern Approach, 4th Edition
1.1
a. Dictionary Definitions Of Intelligence Talk About ―The Capacity To Acquire
And Apply Knowledge‖ Or ―The Faculty Of Thought And Reason‖ Or ―The
Ability To Comprehend And Profit From Experience.‖ These Are All Reasonable
Answers, But If We Want Something Quantifiable We Would Use Something
Like ―The Ability To Apply Knowledge In Order To Perform Better In An
Environment.‖
b. We Define Artificial Intelligence As The Study And Construction Of Agent
Programs That Perform Well In A Given Environment, For A Given Agent
Architecture.
c. We Define An Agent As An Entity That Takes Action In Response To Percepts
From An Envi- Ronment.
1.2 See The Solution For Exercise 26.1 For Some Discussion Of Potential Objections.
The Probability Of Fooling An Interrogator Depends On Just How Unskilled
The Interroga- Tor Is. One Entrant In The 2002 Loebner Prize Competition (Which Is
Not Quite A Real Turing Test) Did Fool One Judge, Although If You Look At The
Transcript, It Is Hard To Imagine What That Judge Was Thinking. There Certainly
Have Been Examples Of A Chatbot Or Other Online Agent Fooling Humans. For
Example, See See Lenny Foner’s Account Of The Julia Chatbot At
Foner.Www.Media.Mit.Edu/People/Foner/Julia/. We’d Say The Chance Today Is
Something Like 10%, With The Variation Depending More On The Skill Of The
Interrogator Rather Than The Program. In 50 Years, We Expect That The
Entertainment Industry (Movies, Video Games, Com- Mercials) Will Have Made
Sufficient Investments In Artificial Actors To Create Very Credible Impersonators.
1.3 The 2002 Loebner Prize (Www.Loebner.Net) Went To Kevin Copple’s Program
ELLA. It Consists Of A Prioritized Set Of Pattern/Action Rules: If It Sees A Text String
Matching A Certain Pattern, It Outputs The Corresponding Response, Which May
Include Pieces Of The Current Or Past Input. It Also Has A Large Database Of Text
And Has The Wordnet Online Dictionary. It Is Therefore Using Rather Rudimentary
Tools, And Is Not Advancing The Theory Of AI. It Is Provid-
Solution Manual Page
, Artificial Intelligence: A Modern Approach, 4th Edition
Ing Evidence On The Number And Type Of Rules That Are Sufficient For Producing
One Type Of Conversation.
1.4 No. It Means That AI Systems Should Avoid Trying To Solve Intractable
Problems. Usually, This Means They Can Only Approximate Optimal Behavior. Notice
That Humans Don’t Solve NP- Complete Problems Either. Sometimes They Are Good
At Solving Specific Instances With A Lot Of
Structure, Perhaps With The Aid Of Background Knowledge. AI Systems Should
Attempt To Do The Same.
1.5 No. IQ Test Scores Correlate Well With Certain Other Measures, Such As
Success In College, But Only If They’re Measuring Fairly Normal Humans. The IQ Test
Doesn’t Measure Everything. A Program That Is Specialized Only For IQ Tests (And
Specialized Further Only For The Analogy Part) Would Very Likely Perform Poorly
On Other Measures Of Intelligence. See The Mismea- Sure Of Man By Stephen Jay
Gould, Norton, 1981 Or Multiple Intelligences: The Theory In Practice By Howard
Gardner, Basic Books, 1993 For More On IQ Tests, What They Measure, And What
Other Aspects There Are To ―Intelligence.‖
1.6 Just As You Are Unaware Of All The Steps That Go Into Making Your Heart
Beat, You Are Also Unaware Of Most Of What Happens In Your Thoughts. You Do
Have A Conscious Awareness Of Some Of Your Thought Processes, But The
Majority Remains Opaque To Your Consciousness. The Field Of Psychoanalysis Is
Based On The Idea That One Needs Trained Professional Help To Analyze One’s
Own Thoughts.
1.7
a. (Ping-Pong) A Reasonable Level Of Proficiency Was Achieved By Andersson’s
Robot (An- Dersson, 1988).
b. (Driving In Cairo) No. Although There Has Been A Lot Of Progress In
Automated Driving, All Such Systems Currently Rely On Certain Relatively
Constant Clues: That The Road Has Shoulders And A Center Line, That The Car
Ahead Will Travel A Predictable Course, That Cars Will Keep To Their Side Of
Solution Manual Page
, Artificial Intelligence: A Modern Approach, 4th Edition
The Road, And So On. To Our Knowledge, None Are Able To Avoid Obstacles
Or Other Cars Or To Change Lanes As Appropriate; Their Skills Are Mostly
Confined To Staying In One Lane At Constant Speed. Driving In Downtown
Cairo Is Too Unpredictable For Any Of These To Work.
c. (Shopping At The Market) No. No Robot Can Currently Put Together The Tasks
Of Moving In A Crowded Environment, Using Vision To Identify A Wide Variety
Of Objects, And Grasping The Objects (Including Squishable Vegetables)
Without Damaging Them. The Component Pieces Are Nearly Able To Handle
The Individual Tasks, But It Would Take A Major Integra- Tion Effort To Put It
All Together.
Solution Manual Page
