Week 2

Appropriate Scope and Level of Understanding (Criteria for Building an Expert System)

- A problem that has too wide scope or requires too deep level of understanding is not appropriate for an ES. - An ES solves specific problems.

Explanation Facilities (4 Components of an Expert System)

- An expert system must be able to explain its reasoning and justify its advice, analysis or conclusion. - Enable the user to ask the expert system how a particular conclusion is reached and why a specific fact is needed.

Knowledge Engineer (4 Main Players in the Development Team)

- Capable of designing, building, and testing an expert system. - He/She interviews the domain expert to find out how a particular problem is solved. - He/She establishes what reasoning methods the expert uses to handle facts and rules decides how to represent them in the expert system. - He/She then chooses some development software or an expert system shell or looks at programming languages for encoding the knowledge. - Finally, he/she is responsible for testing, revising and integrating the expert system into the workplace.

Forward Chaining (Figure 2)

- Data. - Rule. - Conlusion

Lack of Meta-Knowledge

- Do not have sophisticated knowledge about their own operation. - Cannot reason about their own scope and limitation.

When We Use an Expert Systems

- Final users agree that payoff will be high. - Application is knowledge intensive. - A human expert exists. - Not a natural-language intensive application. - A wide range of test cases are available. - Neither creativity nor physical skills are required.

infer, goal, fact

- Forward chaining is a technique for gathering information and then ______ring from it whatever can be ______red. - However, in forward chaining, many rules may be executed that have nothing to do with the established ____. - Therefore, if our goal is to infer only one particular ____, the forward chaining inference technique would not be efficient.

Problem Has a Definable Solution (Criteria for Building an Expert System)

- If all of the possible solutions cannot be specified; Writing rules to solve the problem is difficult.

information, solution

- If an expert first needs to gather some ___________ and then tries to infer from it whatever can be inferred, choose the forward chaining inference engine. However, if the expert beings with a hypothetical ________ and then attempts to find facts to prove it, choose the backward chaining inference engine.

Problem is Solvable by Humans (Criteria for Building an Expert System)

- If no human expert exists, it is not possible to develop rules describing the problem. - The techniques of solving the problem must be known and defined in order to create an expert system.

Knowledge Acquisition

- It is a bottleneck in applying ES technology to new domains - Validation of an ES is difficult. - Expert systems can make mistakes.

true, confidence

- One of the most powerful parts of an expert system is being able to create rules which state that the answer is probably, but not definitely, ____. - Process accomplished by assigning __________ modes.

Brittleness

- Only have access to highly specific domain knowledge. - Cannot fall back on more general knowledge when needed.

End-User (4 Main Players in the Development Team)

- Person who uses the expert system when it is developed. - The design of the user interface of the expert system is vital for the project's success; the end user's contribution here can be crucial.

Programmer (4 Main Players in the Development Team)

- Responsible for the actual programming, describing the domain knowledge in terms that a computer can understand. - Needs to have skills in symbolic programming in such AI languages as LISP, Prolog and OPS5, some experience in the application of different types of expert system shells. - Should know conventional programming languages like C++, Java, and etc.

Problem Solving Techniques Are Documented (Criteria for Building an Expert System)

- Solution may be decision tree, manual procedure, written instructions, etc. - Well-defined problems can be easily converted to an ES.

Backward Chaining (Goal-Driven) Reasoning

- The expert system has the goal, and the inference engine attempts to find the evidence to prove it. - First, the knowledge base is searched to find rules that might have the desired solution. - Such rules must have the goal in their THEN (action) parts. - If such a rule is found and its IF (condition) part matches data in the database, then the rule is fired, and the goal is proved. - Thus, the inference engine puts aside the rule it is working with (the rule is said to stack) and sets up a new goal, a sub goal, to prove the IF part of this rule. - Then the knowledge base is searched again for rules that can prove the sub goal. - The inference engine repeats the process of stacking the rules until no rules are found in the knowledge base to prove the current sub goal.

Project Manager (4 Main Players in the Development Team)

- The leader of the expert system development team. - Responsible for keeping the project on track. - He/she makes sure that all deliverables and milestones are met, interacts with expert, knowledge engineer, programmer, and end-user.

Factors Used to Compare Human Expert and System Expert

- Time availability. - Geographic. - Safety. - Perishable/consumable. - Performance - Speed. - Cost

When to Use Case-Based Reasoning (CBR)

- When the user wants to browse similar cases. - When you have lots of typical situations or cases for the knowledge base.

When to Use Rule-Based Reasoning (RBR)

- When there is a lot of specific expert knowledge on a particular subject and the expert can solve the problem sequentially. - When an explanation or an audit trail of the solution is required.

Verification, Validation

- ____________: Am I building the product right? - __________: Am I building the right product?

Ways to Assign Confidence Modes

-> 0 - 10 -> -100 - 100 -> Increment/decrement system -> Custom formula

6 Case-Based ES Components

1) Case Base 2) Retriever 3) Adapter 4) Refiner 5) Executer 6) Evaluator

2 Control Strategies for Execution Rules

1) Forward Chaining 2) Backward Chaining

4 Components of an Expert System

1) Knowledge Base 2) Inference Engine 3) Explanation Facilities 4) User Interface

4 Main Players in the Development Team

1) Knowledge Engineer. 2) Programmer. 3) Project Manager 4) End-User.

Two Meta-Rules

1) Meta-Rule 1 2) Meta-Rule 2

5 Rule Representations

1) Relation 2) Recommendation 3) Directives 4) Strategies 5) Heuristics

3 Disadvantages of an ES

1- Brittleness. 2- Lack of Meta-Knowledge. 3- Knowledge Acquisition.

4 Prominent Expert Systems

1- EXSYS 2- DENDRAL 3- MYCIN 4- CADUCEUS

Expert System Strengths

1. Corporate knowledge retained. 2. Knowledge can be incomplete -- the expertise can be expanded as needed. Conventional programs must be "complete" before they can be used. 3. Expert systems can act as consultant, instructor, or partner/colleague.

Expert System Limitations

1. Domain must often be restricted or narrow. 2. Determination of expertise reliability and completeness is very difficult. 3. Some knowledge doesn't translate well to rules/cases. 4. Expert systems are expensive -- problem must be sufficiently complex to justify the cost.

Methods used for Conflict Resolution

1. Fire the rule with the highest priority. 2. Fire the most specific rule. 3. Fire the rule that uses the data most recently entered. 4. (from comment) Establish a goal and stop firing rules when the goal is achieved.

6 Reasons Why We Use an Expert System

1. Frees expert from repetitive, routine jobs. 2. Provides the beginner with expert advice on a specific subject. 3. Wide distribution of rare human knowledge. 4. Aids in training new employees. 5. Improves worker productivity. 6. Provides second opinion in critical situations; especially valuable when tired or under stress.

Criteria for Building an Expert System

1. Problem is solvable by human. 2. Problem has a definable solution. 3. Appropriate scope and level of understanding. 4. Problem solving techniques are documented.

8 Technical Advantages of an Expert System

1. Rapid prototype development. 2. Easier verification of software. 3. Easier maintenance of software. 4. Explains its reasoning in English to user when requested. 5. Truly self-documenting software. 6. Easier to learn to build rule-based expert systems. 7. Inexpensive technology. 8. Automated consistency checking of knowledge in the KB.

Refiner (6 Case-Based ES Components)

A _______ critiques the adapted solution against prior outcomes. - One way to do this is to compare it to similar solutions of prior cases. - If a known failure exists for a derived solution, the system then decides whether the similarities is sufficient to suspect that the new solution will fail.

Expert System (ES) (Def. 1)

A computer program designed to model the problem-solving ability of a human expert.

Expert System (Def. 3)

A computer system which emulates the decision-making ability of a human expert.

Knowledge Engineering

A field within artificial intelligence that develops knowledge-based systems. - Such systems are computer programs that contain large amounts of knowledge, rules and reasoning mechanisms to provide solutions to real-world problems.

conflict resolution

A method for choosing a rule to fire when more than one rule can be fired in a given cycle is called ________ __________.

Expert System (Def. 2)

A model and associated procedure that exhibit, within a specific domain, a degree of expertise in problem solving that is comparable to that of a human expert.

Knowledge Engineer (Personnel Involvement in ES)

A person who designs, develops, and implements expert systems (or other artificial intelligent applications).

Domain Expert (Personnel Involvement in ES)

A person who possesses some skills that allow him/her to draw upon past experiences and quickly focus on the core of a given problem. - Anyone can be considered a ______ ______ if he or she has deep knowledge (of both facts and rules) and strong practical experience in a particular domain.

User (Personnel Involvement in ES)

A person who will use the expert system and eventually benefit from the domain expert's knowledge.

Knowledge Engineer

A professional engaged in the science of building advanced logic into computer systems in order to try to simulate human decision-making and high-level cognitive tasks. - A _________ ________ supplies some or all of the "knowledge" that is eventually built into the technology.

AND, OR

A rule can have multiple conditions joined by the keywords ___(conjunction), __(disjunction) or a combination of both.

Adapter (6 Case-Based ES Components)

An _______ examines the differences between these cases and the current problem using a similarity function. - It then applies rules to modify the old solution to fit the new problem.

case-based

Another way to represent knowledge base is ____-_____ representation (CBR).

An Example of a Conflict

Both of rule 2 and 3 can be set to fire when the condition part is satisfied. - These rules represent a conflict set. - The inference engine must determine which rule to fire from such as set.

Decision Support System

Computer-based support systems which help decision makers utilize data and models to solve semi-structured or unstructured problems.

Forward Chaining Example

Conclude from "A" and "A implies B" to "B". - if A -> B

Backward Chaining Example

Conclude from "B" and "A implies B" to "A".

Expert System

Decision making and/or problem-solving package that can reach a level of performance comparable to (or even exceeding that of) a human expert in some specialized and usually narrow problem area.

Scope and Level of Understanding (Figure)

Defining the problem to fall within the shaded area of the graph is very important.

DENDRAL

Embedded a chemist's knowledge of mass spectrometry rules to use in analysis.

Expert System, Intelligent Agent

Every (Expert System/Intelligent Agent) is considered an (Expert System/Intelligent Agent), but not vice versa.

Intelligent Agent, Expert System

From an (Expert System/Intelligent Agent) I am expected to find a high capability to adapt the functioning to a wide range of changeable in environment conditions. Instead, for an (Expert System/Intelligent Agent) I will find a very specialized system in some tasks.

education

Heuristic _________ is based on discovering and experiencing things for yourself.

FC, BC

How do we choose between BC and FC? Follow how a domain expert solves the problem. -> If the expert first collects data and then infer from it => __. -> If the expert starts with a hypothetical solution and then attempts to find facts to prove => __.

Relation (5 Rule Representations)

IF the 'fuel tank is empty' THEN the car is dead

Recommendation (5 Rule Representations)

IF the season is autumn AND the sky is cloudy AND the forecast is slightly rain THEN the advice is 'take an umbrella'

Strategy (5 Rule Representations)

If the car is dead THEN action is 'check the fuel tank'; Step 1 is complete IF step 1 complete AND the 'fuel tank' is full THEN the action is 'Check the battery'; Step is complete

Directive (5 Rule Representations)

If the car is dead AND the 'fuel tank' is empty THEN the actions is 'refuel the car'

Evaluator (6 Case-Based ES Components)

If the results are as expected, no further analysis is made, and the cases with its solution is stored for use in future problem solving. - If not, the solution is repaired.

Heuristic (5 Rule Representations)

If the spill is liquid AND the 'spill pH' < 6 AND the 'spill smell' is vinegar THEN the 'spill meterial' is 'accetic acid' -Expert systems can also use mathematical operators to define an object as numerical and assign it to the numerical value. IF 'age of the customer'<18 AND 'cash withdrawal'>1000 THEN signature of the present's required.

rule-based

In a ____-_____ expert system, the knowledge is represented as a set of rules. - Each rule specifies a relation, recommendation, directive, strategy, or heuristic and has the IF (condition) THEN (action) structure. - ELSE part is the same as the THEN part and is applied if any of the IF conditions are FALSE. - ELSE part is optional and not needed in most rules.

IF-THEN, facts

In a rule-based expert system, the domain knowledge is represented by a set of __-____ production rules and the data is represented by a set of _____ about the current situation.

meta-rules

In rule-based expert systems, meta-knowledge is represented by ____-_____.

Specification (Building an Expert System)

In which, user/expert and knowledge engineer work together to define the objects of the expert system application, including inputs, outputs, and methodology.

Deployment (Building an Expert System)

In which: - Installing the system for routine use. - Fix bugs, update, enhance. -> Go back to development phase. -> This loop remains active throughout the life cycle of the project.

Development (Building an Expert System)

In which: - Knowledge engineer learns how the expert perform tasks (knowledge acquisition). Current, historical, and hypothetical cases must be covered. - Developing a conceptual model of the ES. -> Framework consists of high-level descriptions of the tasks and situations. -> Deciding how the inference, representation, and control structure can be used to replicate the decision process. -> Building the knowledge. - Verifying and Validating

Analysis (Building an Expert System)

In which: - The user/expert identifies a potential application. - The knowledge engineer: -> Is expert system the answer? -> Task is well understood. -> Expertise exists, is reliable, and the solution is generally agreed upon. -> Task is not too hard (but not too easy, either).

Backward Chaining (2 Control Strategies for Execution Rules)

It begins with a goal and works backwards towards the initial conditions will help in answering it.

Inference Engine (4 Components of an Expert System)

It carries out the reasoning whereby the expert system reaches a solution. - Expert systems employ symbolic reasoning when solving a problem. - Symbols are used to represent different types of knowledge such as facts, concepts and rules. - It links the rules given in the knowledge base with the facts provided by the user.

Knowledge Base (4 Components of an Expert System)

It contains the domain knowledge useful for problem solving.

Meta-Rule

It determines a strategy for the use of task-specific rules in the expert system.

Case Base (6 Case-Based ES Components)

It functions as a repository of prior cases. - The cases are indexed so that they can be quickly recalled when necessary. - A case contains the general descriptions of old problems.

Personnel Involvement in ES

It includes: - Domain Expert. - User. - Knowledge Engineer.

Building an Expert System

It involves: 1) Analysis 2) Specification 3) Development 4) Deployment

Fire the Most Specific Rule (Methods used for Conflict Resolution)

It is based on the assumption that a specific rule processes more information than a general one. - This method is also known as the longest matching strategy.

Meta-Knowledge

It is knowledge about the use and control of domain knowledge in an expert system. - It can be simply defined as knowledge about knowledge.

EXSYS

It provides an easy to user interface to develop traditional applications or web-based solutions.

Case-Based Representation (CBR)

It retrieves cases relevant to the present problem situation from the case base and decides on the solution to the current problem on the basis of the outcomes from previous cases.

Forward Chaining (2 Control Strategies for Execution Rules)

It starts with the facts, and sees what rules apply (and hence what should be done) given the facts.

Tree Structure Rules: Model (Figure)

Items of a desk to include a telephone, a computer, a pencil, a legal paper, and a floppy disk.

Executor (6 Case-Based ES Components)

Once a solution is critiqued, an ________ applies the refined solution to the current problem.

Converting Tree Structure to an Expert System

Rule 1: IF the item makes noise AND the color is black -> THEN telephone - Confidence 9/10. Rule 2: IF the item makes noise AND the color is white -> THEN computer - Confidence 10/10. Rule 3: IF the item does not make noise AND the color is black -> THEN floppy disk - Confidence 10/10. Rule 4: IF the item does not make noise AND the color is yellow AND the shape is rectangle -> THEN legal paper - Confidence 7/10. Rule 5: IF the items does not make noise AND the color is yellow AND the shape is cylindrical -> THEN Pencil - Confidence 8/10.

Meta-Rule 2 (Two Meta-Rules)

Rules governing the rescue of human lives have higher priorities than rules concerned with clearing overloads on power system equipment.

Meta-Rule 1 (Two Meta-Rules)

Rules supplied by experts have higher priorities than rules supplied by novices.

inference engine

The _________ ______ compares each rule stored in the knowledge base with facts contained in the database. - When the IF (condition) part of the rule matches a fact, the rule is fired and its THEN (action) part is executed.

User Interface (4 Components of an Expert System)

The means of communication between a user seeking a solution to the problem and an expert system.

Fire the Rule with the Highest Priority (Methods used for Conflict Resolution)

The priority can be established by placing the rules in an appropriate order in the knowledge base.

Forward Chaining (Data-Driven) Reasoning

The reasoning starts from the known data and proceeds forward with that data. - Each time only the topmost rule is executed. - When fired, the rule adds a new fact to the database. - Any rule can be executed only once. - The match-fire cycle stops when no further rules can be fired.

Fire the Rule that Uses the Data Most Recently Entered (Methods used for Conflict Resolution)

This method relies on time tags attached to each fact in the database. In the conflict set, the expert system first fires the rule whose antecedent uses the data most recently added to the database.

backward chaining

Use ____ ____ for diagnostic problems.

forward chaining

Use _______ ________ if all facts available up front.

CADUCEUS

Used to analyze blood-borne infectious bacteria.

MYCIN

Used to diagnose infectious blood diseases and recommend antibiotics.

Retriever (6 Case-Based ES Components)

When a new problem is entered into a case-based system: - A _________ decides on the features similar to the stored cases.

high, reasonable

When it comes to Cost: Human Expert: _____. Expert System: ________.

local, anywhere

When it comes to Geographic: Human Expert: _____. Expert System: ________.

variable, consistent

When it comes to Performance: Human Expert: _____. Expert System: ________.

yes, no

When it comes to Perishable/consumable: Human Expert: _____. Expert System: ________.

irreplaceable, replaceable

When it comes to Safety: Human Expert: _____________. Expert System: ___________.

variable, consistent (usually faster)

When it comes to Speed: Human Expert: _____. Expert System: ________.

workday, always

When it comes to Time Availability: Human Expert: _______. Expert System: ______.

CBR, RBR

___: It is the process of solving new problems based on the solutions of similar past problems. ___: Prolog

Retrieval

_________ is done by using features of the new cases as indexes into the case base.