Introduction to Artificial Intelligence 2067

Artificial Intelligence (AI) is the part of computer science concerned with designing intelligence computer systems i.e. systems that exihibit the characteristics we associate with intelligence in human behaviour.

The behaviours of AI are as follows:

1. Learn from experience and apply knowledge acquired from experience

2. Handle Complex Situations

3. Solve problems with important information is missing: Decision must be made even when we lack information or have inaccurate information.

4. Determine what is important

5. React quickly and correctly to a new situation

6. Understand visual images

7. Process and manipulate symbols

8. Be creative and imaginative

9. Use heuristics

Turing Test

The Turing test, proposed by Alan Turing  was designed to convince the people that whether a particular machine can think or not. The test involves an interrogator who interacts with one human and one machine. Within a given time the interrogator has to find out which of the two the human is, and which one the machine.

To pass a Turing test, a computer must have following capabilities:

• Natural Language Processing: To communicate easily.
• Knowledge Representation: To store facts and rules.
• Automated Reasoning: To draw conclusion from stored knowledge.
• Machine Learning: To adopt new circumstances and detect pattern.

Additional requirements for the “total Turing test”: computer vision, speech recognition, speech synthesis, robotics.

A sentence that is expressed as a disjunction of conjuction of literals is said to be in disjunctive normal form (DNF). E.g. (P∧Q)∨(P∧R)

DNF conversion steps

1. Eliminate ↔ rewriting P↔Q as (P→Q)∧(Q→P)

2. Eliminate → rewriting P→Q as ¬P∨Q

3. Use De Morgan‘s laws to push ¬ inwards:

        - rewrite ¬(P∧Q) as ¬P∨¬Q

        - rewrite ¬(P∨Q) as ¬P∧¬Q

4. Eliminate double negations: rewrite ¬¬P as P

5. Use the distributive laws to get DNF:

        - rewrite P∧(Q∨R) as (P∧Q)∨(P∧R)

6. Use:

        - (P∧Q) ∧ R as P∧Q ∧ R

        - (P∨Q)∨R as P∨Q∨R

Inference: Inference is a process by which new sentences are derived from existing sentences in KB. E.g. Modus tollens is a rule of inference which derives new knowledge.

Reasoning: Reasoning is the act of deriving a conclusion from certain premise using given methodology.

 Probabilistic reasoning is using logic and probability to handle uncertain situations. The aim of probabilistic reasoning is to combine the capacity of probability theory to handle uncertainity with the capacity of deductive logic to exploit structure of formal argument.

Probabilistic reasoning is used in AI:

• When we are unsure of the predicates
• When the possibilities of predicates become too large to list down
• When it is known that an error occurs during an experiment

One has to apply probabilistic reasoning in deciding about the next card to play in a game of cards or in diagnosing the illness from the symptoms.

AI problems can be readily modeled as state spaces, where we want to find the best possible solution, that successfully solves a particular task, among all the available candidate solutions in the solution space. Using different searching algorithms we can find the best possible solution. So searching is important in AI.

Breadth First Search

It expands the shallowest unexpanded node first. Starting from the root node (initial state) explores all children of the root node, left to right. If no solution is found, expands the first (leftmost) child of the root node, then expands the second node at depth 1 and so on …until a solution is found.

E.g.

Depth First Search

It expands the deepest unexpanded node first.

It expands the root node, then the leftmost child of the root node, then the left most child of that node and so on. Only when the search hits dead end does the search backtrack.

E.g.

Learning is acquiring new or modifying existing knowledge, behaviors, skills and may involve synthesizing different types of information.

A Machine Learning Framework is an interface, library or tool which allows developers to more easily and quickly build machine learning models. Learning framework is required because it provides a clear, concise way for defining machine learning models using a collection of pre-built, optimized components. 

Learning Framework:

It consists of the following components:

• Learning element: This element is responsible for making improvements.
• Performance element: It is responsible for selecting external actions according to the percepts it takes.
• Critic: It provides feedback to the learning agent about how well the agent is doing, which could maximize the performance measure in the future.
• Problem Generator: It suggests actions which could lead to new and informative experiences.

Example:

Performance element: turning, accelerating, breaking are the performance elements on road.

Learning element: learn rules for breaking, accelerating, learn geography of the city.

Critic: quick right turn across three lanes of traffic, observes reaction of other drivers.

Problem generator: Try south city road.

Baye's theorem is a way to apply conditional probability for prediction. Conditional probability is the probability of an event happening, given that it has some relationship to one or more other events.

Mathematically, Baye's theorem is defined as:

Bayes theorem provides a way to resolve existing predictions or theories (update probabilities) given new or additional evidence. This, in turn, makes the prediction more accurate.

Applications of Bayes theorem:

1.  Medical science: Baye's rule is used for predicting a particular disease based on the symptoms and physical condition of the patient.

2. Weather forcasting: Baye's rule is a powerful algorithm for predictive modeling weather forcast.

3. Robotics: Baye's rule is used to calculate the probability of a robot's next steps given the steps the robot has already executed.

4. Finance: Baye's theorem can be used to rate the risk of lending money to potential borrowers.

    etc.

Backpropagation is a supervised learning method, and is an implementation of the Delta rule. It requires a teacher that can calculate the desired output for any given input.

Steps / Algorithms

Example

After updating weights, we recompute y. Then we compute δ=t-y. If the value of y is converges to t then the values is fixed up otherwise we will iterate again.

An expert system is a set of program that manipulate encoded knowledge to solve problem in a specialized domain that normally requires human expertise.

We can construct expert system using given steps as below:

Knowledge Engineering

Knowledge engineering is a field of AI that creates rules to apply data in order to initiate the thought process of human expert. Knowledge engineering attempts to take challenges and solve problems that would usually require a high level of human expertise to solve.

In general, knowledge engineering is the process of understanding and representing a human knowledge in a computer as a program. Knowledge engineering includes:

1) Knowledge acquisition

2) Knowledge representation

3) Knowledge validation

4) Inferencing

5) Explanation and justification

            The interaction between these stages and source of knowledge is shown in the figure below:

Natural language processing is a technology which involves converting spoken or written human language into a form which can be processed by computers, and vice versa. NLP is composed of two parts: NLU and NLG.

Issues involved in the natural language processing are given below:

1. The same expression means different things in different context.

·         Where’s the water? ( Chemistry lab? Must be pure)

·         Where’s the water? ( Thirsty? Must be drinking water)

·         Where’s the water? ( Leaky roof? It can be dirty)

2. No natural language program can be complete because of new words, expression, and meaning can be generated quite freely.

·         I’ll fax it to you

3.  There are lots of ways to say the same thing.

·         Ram was born on October 11.

·         Ram’s birthday is October 11.

4.  Sentence and phrases might have hidden meanings

•      “Out of sight, out of mind”-> “ invisible idiot”

•      “The spirit was willing but the flesh was weak” - > “ the vodka was good, but the meat was bad”

5.  Problem due to syntax and semantics

6.  Problem due to extensive use of pronouns. (semantic issue)

•      Eg. Ravi went to the supermarket. He found his favorite brand of coffee in rack. He paid for it and left.

•      It denotes??

7.  Use of grammatically incorrect sentence

•      He rice eats. (syntax issue)

8.  Use of conjunctions to avoid repetition of phrases cause problem in NLP

•      Eg. Ram and Hari went to restaurant. While Ram had a cup of coffee, Hari had tea.

•      Hari had a cup of tea.