Based on the provided data, I do not have enough information to make an accurate diagnosis. Some key data points that would be helpful include: - Details on any symptoms (e.g. chest pain type if present) - ECG or imaging test results - Family history of heart disease - Whether the patient smokes - Details on lifestyle factors like diet, exercise and stress levels Without more clinical context, I cannot determine if this patient shows signs of heart disease or what the likely diagnosis may be. Please provide additional medical history if you would like me to try assessing this case.

1. UNIT 4
PLANNING AND MACHINE
LEARNING
UNIT 4
PLANNING AND MACHINE
LEARNING

2. Planning
•Definition : Planning is arranging a sequence of
actions to achieve a goal.
•Uses core areas of AI like searching and reasoning &
•Is the core for areas like NLP, Computer Vision.
•Robotics
•Examples : Navigation , Manoeuvring, Language
Processing (Generation)
•Definition : Planning is arranging a sequence of
actions to achieve a goal.
•Uses core areas of AI like searching and reasoning &
•Is the core for areas like NLP, Computer Vision.
•Robotics
•Examples : Navigation , Manoeuvring, Language
Processing (Generation)
Kinematics (ME)
Planning (CSE)

3. Language & Planning
• Non-linguistic representation for sentences.
•Sentence generation
•Word order determination (Syntax planning)
E.g. I see movie ( English)
I movie see (Intermediate Language)
see
I movie
agent object
• Non-linguistic representation for sentences.
•Sentence generation
•Word order determination (Syntax planning)
E.g. I see movie ( English)
I movie see (Intermediate Language)
I movie

4. STRIPS
•Stanford Research Institute Problem Solver (1970s)
•Planning system for a robotics project : SHAKEY (by
Nilsson et.al.)
•Knowledge Representation : First Order Logic.
•Algorithm : Forward chaining on rules.
•Any search procedure : Finds a path from start to goal.
•Forward Chaining : Data-driven inferencing
•Backward Chaining : Goal-driven
•Stanford Research Institute Problem Solver (1970s)
•Planning system for a robotics project : SHAKEY (by
Nilsson et.al.)
•Knowledge Representation : First Order Logic.
•Algorithm : Forward chaining on rules.
•Any search procedure : Finds a path from start to goal.
•Forward Chaining : Data-driven inferencing
•Backward Chaining : Goal-driven

5. Example : Blocks World
•STRIPS : A planning system – Has rules with
precondition deletion list and addition list
A
C
A
C
B
B
START GOAL
Robot
hand
Robot
hand
START GOAL
Sequence of actions :
1. Grab C
2. Pickup C
3. Place on table C
4. Grab B
5. Pickup B
6. Stack B on C
7. Grab A
8. Pickup A
9. Stack A on B

6. Example : Blocks World
•Fundamental Problem :
The frame problem in AI is concerned with the question
of what piece of knowledge is relevant to the situation.
•Fundamental Assumption : Closed world assumption
If something is not asserted in the knowledge base, it is
assumed to be false.
(Also called “Negation by failure”)
•Fundamental Problem :
The frame problem in AI is concerned with the question
of what piece of knowledge is relevant to the situation.
•Fundamental Assumption : Closed world assumption
If something is not asserted in the knowledge base, it is
assumed to be false.
(Also called “Negation by failure”)

7. Example : Blocks World
•STRIPS : A planning system – Has rules with
precondition deletion list and addition list
A
C
A
C
B
B
START GOAL
Robot
hand
Robot
hand
on(B, table)
on(A, table)
on(C, A)
hand empty
clear(C)
clear(B)
on(C, table)
on(B, C)
on(A, B)
hand empty
clear(A)
START GOAL

8. Rules
•R1 : pickup(x)
Precondition & Deletion List : hand empty,
on(x,table), clear(x)
Add List : holding(x)
•R2 : putdown(x)
Precondition & Deletion List : holding(x)
Add List : hand empty, on(x,table), clear(x)
•R1 : pickup(x)
Precondition & Deletion List : hand empty,
on(x,table), clear(x)
Add List : holding(x)
•R2 : putdown(x)
Precondition & Deletion List : holding(x)
Add List : hand empty, on(x,table), clear(x)

9. Rules
•R3 : stack(x,y)
Precondition & Deletion List :holding(x), clear(y) Add
List : on(x,y), clear(x)
•R4 : unstack(x,y)
Precondition & Deletion List : on(x,y), clear(x)
Add List : holding(x), clear(y)
•R3 : stack(x,y)
Precondition & Deletion List :holding(x), clear(y) Add
List : on(x,y), clear(x)
•R4 : unstack(x,y)
Precondition & Deletion List : on(x,y), clear(x)
Add List : holding(x), clear(y)

10. Plan for the block world problem
• For the given problem, Start  Goal can be achieved
by the following sequence :
1. Unstack(C,A)
2. Putdown(C)
3. Pickup(B)
4. Stack(B,C)
5. Pickup(A)
6. Stack(A,B)
• Execution of a plan: achieved through a data structure
called Triangular Table.
• For the given problem, Start  Goal can be achieved
by the following sequence :
1. Unstack(C,A)
2. Putdown(C)
3. Pickup(B)
4. Stack(B,C)
5. Pickup(A)
6. Stack(A,B)
• Execution of a plan: achieved through a data structure
called Triangular Table.

11. Triangular Table
holding(C)
unstack(C,A)
putdown(C)
hand empty
on(B,table) pickup(B)
clear(C) holding(B) stack(B,C)
clear(C)
on(C,A)
hand empty
1
2
3
4 clear(C) holding(B) stack(B,C)
on(A,table) clear(A) hand empty pickup(A)
clear(B) holding(A) stack(A,B)
on(C,table) on(B,C) on(A,B)
clear(A)
0 1 2 3 4 5 6
4
5
6
7

12. Triangular Table
• For n operations in the plan, there are :
• (n+1) rows : 1  n+1
• (n+1) columns : 0  n
• At the end of the ith row, place the ith component of the plan.
• The row entries for the ith step contain the pre-conditions for the
ith operation.
• The column entries for the jth column contain the add list for the
rule on the top.
• The <i,j> th cell (where 1 ≤ i ≤ n+1 and 0≤ j ≤ n) contain the pre-
conditions for the ith operation that are added by the jth operation.
• The first column indicates the starting state and the last row
indicates the goal state.
• For n operations in the plan, there are :
• (n+1) rows : 1  n+1
• (n+1) columns : 0  n
• At the end of the ith row, place the ith component of the plan.
• The row entries for the ith step contain the pre-conditions for the
ith operation.
• The column entries for the jth column contain the add list for the
rule on the top.
• The <i,j> th cell (where 1 ≤ i ≤ n+1 and 0≤ j ≤ n) contain the pre-
conditions for the ith operation that are added by the jth operation.
• The first column indicates the starting state and the last row
indicates the goal state.

13. Search in case of planning
• Ex: Blocks world
• Triangular table leads
• to some amount of fault-tolerance in the robot
Start
S1 S2
Pickup(B) Unstack(C,A)
• Ex: Blocks world
• Triangular table leads
• to some amount of fault-tolerance in the robot
A
C
B
START
A C
B
A
C B
WRONG
MOVE
NOT ALLOWED

14. Resilience in Planning
• After a wrong operation, can the robot come back to
the right path ?
• i.e. after performing a wrong operation, if the system
again goes towards the goal, then it has resilience
w.r.t. that operation
• Advanced planning strategies
– Hierarchical planning
– Probabilistic planning
– Constraint satisfaction
• After a wrong operation, can the robot come back to
the right path ?
• i.e. after performing a wrong operation, if the system
again goes towards the goal, then it has resilience
w.r.t. that operation
• Advanced planning strategies
– Hierarchical planning
– Probabilistic planning
– Constraint satisfaction

15. K Strips
• Modal Operator K :
We are familiar with the use of connectives ∧
and V in logics.
• Thinking of these connectives as operators
that construct more complex formulas from
simpler components.
• Here, we want to construct a formula whose
intended meaning is that a certain agent
knows a certain proposition.
• Modal Operator K :
We are familiar with the use of connectives ∧
and V in logics.
• Thinking of these connectives as operators
that construct more complex formulas from
simpler components.
• Here, we want to construct a formula whose
intended meaning is that a certain agent
knows a certain proposition.

16. • The components consist of a term denoting
the agent and a formula denoting a
proposition that the agent knows.
• To accomplish this, modal operator K is
introduced.
• For example, to say that Robot (name of
agent) know that block A is on block B, then
write,
K( Robot, On(A,B))
K Strips
• The components consist of a term denoting
the agent and a formula denoting a
proposition that the agent knows.
• To accomplish this, modal operator K is
introduced.
• For example, to say that Robot (name of
agent) know that block A is on block B, then
write,
K( Robot, On(A,B))

17. K Strips
• The sentence formed by combining K with the
term Robot and the formula On(A,B) gets a
new formula, the intended meaning of which
is “Robot knows that block A is on block B”.
• The words “knows” and “belief” is different in
meaning.
• That means an agent can believe a false
proposition, but it cannot know anything that
is false.
• The sentence formed by combining K with the
term Robot and the formula On(A,B) gets a
new formula, the intended meaning of which
is “Robot knows that block A is on block B”.
• The words “knows” and “belief” is different in
meaning.
• That means an agent can believe a false
proposition, but it cannot know anything that
is false.

18. K Strips
• Some examples,
• K(Agent1, K(Agent2, On(A,B) ) ], means Agent1
knows that Agent1 knows that A is on B.
K(Agent1, On(A,B)) V K(Agent1, On(A,C) )
means that either Agent1 knows that A is on B
or it knows that A is on C.
• K(Agent1, On(A,B)) V K(Agent1, ¬On(A,B) )
means that either Agent1 knows whether or
not A is on B.
• Some examples,
• K(Agent1, K(Agent2, On(A,B) ) ], means Agent1
knows that Agent1 knows that A is on B.
K(Agent1, On(A,B)) V K(Agent1, On(A,C) )
means that either Agent1 knows that A is on B
or it knows that A is on C.
• K(Agent1, On(A,B)) V K(Agent1, ¬On(A,B) )
means that either Agent1 knows whether or
not A is on B.

19. K Strips
• Knowledge Axioms:
• The operators ∧ and V have compositional
semantics (depends on truth value) , but the
semantics of K are not compositional.
• The truth value of K(Agent1, On(A,B) ) for
example, cannot necessarily be determined
from the properties of K, the denotation of
Agent1 and the truth value of On(A,B).
• K Operator is said to be referentially opaque.
• Knowledge Axioms:
• The operators ∧ and V have compositional
semantics (depends on truth value) , but the
semantics of K are not compositional.
• The truth value of K(Agent1, On(A,B) ) for
example, cannot necessarily be determined
from the properties of K, the denotation of
Agent1 and the truth value of On(A,B).
• K Operator is said to be referentially opaque.

20. K Strips
• Example in Planning Speech Action:
• We can treat speech acts just like other agent
systems.
• Our agent can use a plan-generating system to
make plans comprising speech acts and other
actions.
• To do so, it needs a model of the effects of
these actions.
• Example in Planning Speech Action:
• We can treat speech acts just like other agent
systems.
• Our agent can use a plan-generating system to
make plans comprising speech acts and other
actions.
• To do so, it needs a model of the effects of
these actions.

21. K Strips
• Consider for example, Tell( A, φ ) , where A is
Agent and φ is true.
We could model the effects of that action by
the STRIPS rule :
• Tell( A, φ ) :
• Precondition : Next_to(A) ∧ φ ∧ ¬K(A, φ)
• Delete : ¬K(A, φ)
• Consider for example, Tell( A, φ ) , where A is
Agent and φ is true.
We could model the effects of that action by
the STRIPS rule :
• Tell( A, φ ) :
• Precondition : Next_to(A) ∧ φ ∧ ¬K(A, φ)
• Delete : ¬K(A, φ)

22. K Strips
• Add : K(A, φ)
• The precondition Next_to(A) ensures that our
agent is close to agent A to enable
communication.
• The precondition φ is imposed to ensure that
our agent actually believes φ before it can
inform another agent about the truth.
• The precondition ¬K(A, φ) ensure that our
agent does not communicate redundant
information.
• Add : K(A, φ)
• The precondition Next_to(A) ensures that our
agent is close to agent A to enable
communication.
• The precondition φ is imposed to ensure that
our agent actually believes φ before it can
inform another agent about the truth.
• The precondition ¬K(A, φ) ensure that our
agent does not communicate redundant
information.

23. Intelligence
• Intelligence
– Ability to solve problems
• Examples of Intelligent Behaviors or Tasks
– Classification of texts based on content
– Heart disease diagnosis
– Chess playing
• Intelligence
– Ability to solve problems
• Examples of Intelligent Behaviors or Tasks
– Classification of texts based on content
– Heart disease diagnosis
– Chess playing

24. Example 1: Text Classification (1)
Huge oil platforms dot the Gulf like beacons
-- usually lit up like Christmas trees at night.
One of them, sitting astride the Rostam
offshore oilfield, was all but blown out of
the water by U.S. Warships on Monday.
The Iranian platform, an unsightly mass of
steel and concrete, was a three-tier
structure rising 200 feet (60 metres) above
the warm waters of the Gulf until four U.S.
Destroyers pumped some …
Human
Judgment
Huge oil platforms dot the Gulf like beacons
-- usually lit up like Christmas trees at night.
One of them, sitting astride the Rostam
offshore oilfield, was all but blown out of
the water by U.S. Warships on Monday.
The Iranian platform, an unsightly mass of
steel and concrete, was a three-tier
structure rising 200 feet (60 metres) above
the warm waters of the Gulf until four U.S.
Destroyers pumped some …
Human
Judgment
Crude
Ship

25. Example 1: Text Classification (2)
The Federal Reserve is expected to enter the
government securities market to supply
reserves to the banking system via system
repurchase agreements, economists said.
Most economists said the Fed would
execute three-day system repurchases to
meet a substantial need to add reserves in
the current maintenance period, although
some said a more …
Human
Judgment
The Federal Reserve is expected to enter the
government securities market to supply
reserves to the banking system via system
repurchase agreements, economists said.
Most economists said the Fed would
execute three-day system repurchases to
meet a substantial need to add reserves in
the current maintenance period, although
some said a more …
Human
Judgment
Money-fx

26. Example 2: Disease Diagnosis (1)
Patient 1’s data
Age: 67
Sex: male
Chest pain type: asymptomatic
Resting blood pressure: 160mm Hg
Serum cholestoral: 286mg/dl
Fasting blood sugar: < 120mg/dl
…
Doctor
Diagnosis
Patient 1’s data
Age: 67
Sex: male
Chest pain type: asymptomatic
Resting blood pressure: 160mm Hg
Serum cholestoral: 286mg/dl
Fasting blood sugar: < 120mg/dl
…
Doctor
Diagnosis
Presence

27. Example 2: Disease Diagnosis (2)
Patient 2‘s data
Age: 63
Sex: male
Chest pain type: typical angina
Resting blood pressure: 145mm Hg
Serum cholestoral: 233mg/dl
Fasting blood sugar: > 120mg/dl
…
Doctor
Diagnosis
Patient 2‘s data
Age: 63
Sex: male
Chest pain type: typical angina
Resting blood pressure: 145mm Hg
Serum cholestoral: 233mg/dl
Fasting blood sugar: > 120mg/dl
…
Doctor
Diagnosis
Absence

28. Example 3: Chess Playing
• Chess Game
– Two players playing one-by-one under the
restriction of a certain rule
• Characteristics
– To achieve a goal: win the game
– Interactive
• Chess Game
– Two players playing one-by-one under the
restriction of a certain rule
• Characteristics
– To achieve a goal: win the game
– Interactive

29. Artificial Intelligence
• Artificial Intelligence
– Ability of machines in conducting intelligent
tasks
• Intelligent Programs
– Programs conducting specific intelligent tasks
• Artificial Intelligence
– Ability of machines in conducting intelligent
tasks
• Intelligent Programs
– Programs conducting specific intelligent tasks
Input
Intelligent
Processing
Output

30. Example 1: Text Classifier (1)
…
fiber = 0
…
huge = 1
…
oil = 1
platforms = 1
…
Classification
…
Crude = 1
…
Money-fx = 0
…
Ship = 1
…
Text File:
Huge oil
platforms dot
the Gulf like
beacons --
usually lit up …
Preprocessing
…
fiber = 0
…
huge = 1
…
oil = 1
platforms = 1
…
Classification
…
Crude = 1
…
Money-fx = 0
…
Ship = 1
…
Text File:
Huge oil
platforms dot
the Gulf like
beacons --
usually lit up …
Preprocessing

31. Example 1: Text Classifier (2)
…
enter = 1
expected = 1
…
federal = 1
…
oil = 0
…
Classification
…
Crude = 0
…
Money-fx = 1
…
Ship = 0
…
Text File:
The Federal
Reserve is
expected to
enter the
government …
Preprocessing
…
enter = 1
expected = 1
…
federal = 1
…
oil = 0
…
Classification
…
Crude = 0
…
Money-fx = 1
…
Ship = 0
…
Text File:
The Federal
Reserve is
expected to
enter the
government …
Preprocessing

32. Example 2: Disease Classifier (1)
Preprocessed data of patient 1
Age = 67
Sex = 1
Chest pain type = 4
Resting blood pressure = 160
Serum cholestoral = 286
Fasting blood sugar = 0
…
Classification
Preprocessed data of patient 1
Age = 67
Sex = 1
Chest pain type = 4
Resting blood pressure = 160
Serum cholestoral = 286
Fasting blood sugar = 0
…
Classification
Presence = 1

33. Example 2: Disease Classifier (2)
Preprocessed data of patient 2
Age = 63
Sex = 1
Chest pain type = 1
Resting blood pressure = 145
Serum cholestoral = 233
Fasting blood sugar = 1
…
Classification
Preprocessed data of patient 2
Age = 63
Sex = 1
Chest pain type = 1
Resting blood pressure = 145
Serum cholestoral = 233
Fasting blood sugar = 1
…
Classification
Presence = 0

34. Example 3: Chess Program
Searching and
evaluating
Best move -New
matrix
Opponent’s
playing his move
Matrix representing the
current board

35. AI Approach
• Reasoning with Knowledge
– Knowledge base
– Reasoning
• Traditional Approaches
– Handcrafted knowledge base
– Complex reasoning process
– Disadvantages
• Knowledge acquisition bottleneck
• Reasoning with Knowledge
– Knowledge base
– Reasoning
• Traditional Approaches
– Handcrafted knowledge base
– Complex reasoning process
– Disadvantages
• Knowledge acquisition bottleneck

36. Machine Learning
• Machine Learning (Mitchell 1997)
– Learn from past experiences
– Improve the performances of intelligent
programs
• Definitions (Mitchell 1997)
– A computer program is said to learn from
experience E with respect to some class of
tasks T and performance measure P, if its
performance at the tasks improves with the
experiences
• Machine Learning (Mitchell 1997)
– Learn from past experiences
– Improve the performances of intelligent
programs
• Definitions (Mitchell 1997)
– A computer program is said to learn from
experience E with respect to some class of
tasks T and performance measure P, if its
performance at the tasks improves with the
experiences

37. Example 1: Text Classification
Classified text files
Text file 1 trade
Text file 2 ship
… …
Text classifier
New text file class
Classified text files
Text file 1 trade
Text file 2 ship
… …
Training

38. Example 2: Disease Diagnosis
Database of medical records
Patient 1’s data Absence
Patient 2’s data Presence
… …
Disease classifier
New patient’s
data
Presence or
absence
Database of medical records
Patient 1’s data Absence
Patient 2’s data Presence
… …
Training

39. Example 3: Chess Playing
Games played:
Game 1’s move list Win
Game 2’s move list Lose
… …
Strategy of
Searching and
Evaluating
New matrix
representing the
current board
Best move
Games played:
Game 1’s move list Win
Game 2’s move list Lose
… …
Training

40. Examples
• Text Classification
– Task T
• Assigning texts to a set of predefined categories
– Performance measure P
• Precision and recall of each category
– Training experiences E
• A database of texts with their corresponding
categories
• How about Disease Diagnosis?
• How about Chess Playing?
• Text Classification
– Task T
• Assigning texts to a set of predefined categories
– Performance measure P
• Precision and recall of each category
– Training experiences E
• A database of texts with their corresponding
categories
• How about Disease Diagnosis?
• How about Chess Playing?

41. Why Machine Learning Is Possible?
• Mass Storage
– More data available
• Higher Performance of Computer
– Larger memory in handling the data
– Greater computational power for calculating
and even online learning
• Mass Storage
– More data available
• Higher Performance of Computer
– Larger memory in handling the data
– Greater computational power for calculating
and even online learning

42. Advantages
• Alleviate Knowledge Acquisition Bottleneck
– Does not require knowledge engineers
– Scalable in constructing knowledge base
• Adaptive
– Adaptive to the changing conditions
– Easy in migrating to new domains
• Alleviate Knowledge Acquisition Bottleneck
– Does not require knowledge engineers
– Scalable in constructing knowledge base
• Adaptive
– Adaptive to the changing conditions
– Easy in migrating to new domains

43. Success of Machine Learning
• Almost All the Learning Algorithms
– Text classification (Dumais et al. 1998)
– Gene or protein classification optionally with
feature engineering (Bhaskar et al. 2006)
• Reinforcement Learning
– Backgammon (Tesauro 1995)
• Learning of Sequence Labeling
– Speech recognition (Lee 1989)
– Part-of-speech tagging (Church 1988)
• Almost All the Learning Algorithms
– Text classification (Dumais et al. 1998)
– Gene or protein classification optionally with
feature engineering (Bhaskar et al. 2006)
• Reinforcement Learning
– Backgammon (Tesauro 1995)
• Learning of Sequence Labeling
– Speech recognition (Lee 1989)
– Part-of-speech tagging (Church 1988)

44. Adaptive Learning

45. Adaptive Learning Basics
• A system which collects user information and behavioral
data to customize a learning experience for an individual
• Encourages active participation rather than passive
receptacle
• Moves away from static hypermedia (same page content
and links for all users)
• Artificial Intelligence movement
• A system which collects user information and behavioral
data to customize a learning experience for an individual
• Encourages active participation rather than passive
receptacle
• Moves away from static hypermedia (same page content
and links for all users)
• Artificial Intelligence movement

46. This…

47. Not this…

48. Machine Learning
• Machine collects data and recognizes patterns in the
data
• Algorithms – sequence of instructions to transform
the input into output
• Intelligent systems have the ability to learn in a
changing environment
• Machine collects data and recognizes patterns in the
data
• Algorithms – sequence of instructions to transform
the input into output
• Intelligent systems have the ability to learn in a
changing environment

49. Adaptation Process
• Data collection
– User interaction
– Direct input
• Interpret data using models
• Infer user requirements and preferences
• Tailored aggregation
• Presentation of tailored content (adaptive
effect)
• Synthesis with population data
• Data collection
– User interaction
– Direct input
• Interpret data using models
• Infer user requirements and preferences
• Tailored aggregation
• Presentation of tailored content (adaptive
effect)
• Synthesis with population data

50. Adaptation Process

51. Modeling

52. Categories of Adaptation
• Interaction with the system
• Course/object delivery
• Content adaptation
• Collaborative/social support
• Interaction with the system
• Course/object delivery
• Content adaptation
• Collaborative/social support

53. Content Adaptation
• Adaptive presentation
– content of a hypermedia page adapted to the user’s
goals, knowledge and other information
• Adaptive navigation
– link presentation and functionality adapted to the
goals, knowledge and characteristics of the user
• Direct guidance
• Link sorting
• Link annotation
• Link hiding
• Adaptive presentation
– content of a hypermedia page adapted to the user’s
goals, knowledge and other information
• Adaptive navigation
– link presentation and functionality adapted to the
goals, knowledge and characteristics of the user
• Direct guidance
• Link sorting
• Link annotation
• Link hiding

54. Assessment
• System feedback
• Embedded assessment
• Adaptive
– Timing/architecture
– Question level
• System feedback
• Embedded assessment
• Adaptive
– Timing/architecture
– Question level

55. Examples
• Adaptive eLearning Research Group
• AHA!
• Andes Physics Tutor
• ELM-ART
• GRE
• iKnow!
• Learnthat
• Khan Academy
• Knewton
• Adaptive eLearning Research Group
• AHA!
• Andes Physics Tutor
• ELM-ART
• GRE
• iKnow!
• Learnthat
• Khan Academy
• Knewton

56. Adaptive vs machine learning
• An adaptive system is a set of interacting or interdependent entities, real
or abstract, forming an integrated whole that together are able to respond
to environmental changes or changes in the interacting parts. Feedback
loops represent a key feature of adaptive systems, allowing the response
to changes; examples of adaptive systems include: natural ecosystems,
individual organisms, human communities, human organizations, and
human families.
• Some artificial systems can be adaptive as well; for instance, robots
employ control systems that utilize feedback loops to sense new
conditions in their environment and adapt accordingly.
• An adaptive system is a set of interacting or interdependent entities, real
or abstract, forming an integrated whole that together are able to respond
to environmental changes or changes in the interacting parts. Feedback
loops represent a key feature of adaptive systems, allowing the response
to changes; examples of adaptive systems include: natural ecosystems,
individual organisms, human communities, human organizations, and
human families.
• Some artificial systems can be adaptive as well; for instance, robots
employ control systems that utilize feedback loops to sense new
conditions in their environment and adapt accordingly.

57. UNIT 4 ENDS!!!