What is monotonic reasoning? In monotonic reasoning, once the conclusion is taken, then it will remain the same even if we add some other information to existing information in our knowledge base. Example: e Earth revolves around the Sun. It is a true fact, and it cannot be changed even if we add another sentence in knowledge base like, "The moon revolves around the earth" Or "Earth is not round," etc. Describe architecture of Truth maintenance Systems. Truth maintenance systems (TMS), alsoknown as reason maintenance systems, are a crucial component of artificial intelligence and knowledge representation. It manages inconsistencies and contradictions, allowing Al systems to reason with incomplete or uncertain information. It works like whenever new information comes and it says that previous information is wrong then the truth maintenance systems justify which one is wrong and which one is right. TMSs are used in a variety of Al applications, such as planning, diagnosis, and natural language processing. The architecture of a TMS typicallyconsists of three main components: Problem Solver Tell Inference engine (IE) Ask Knowledge base Fig: Architecture of Truth Management System (TMS) KnowledgeBase: is basically a database or a storage which stores all the information, facts and rules in structured format. For example, in a medical diagnosis system, the knowledge base might contain information about symptoms, diseases, and relationships between them. As new information is acquired, the knowledge base is updated to reflect the currentstate of knowledge. Inference Engine: The Inference Engine is a component of an Al system responsible for drawing conclusions or making predictions based on the information stored in the knowledge base. It uses logical rules, reasoning mechanisms, or algorithms to process the available information and derive new knowledge. TMS: It is responsible for managing the consistency in knowledge base by asking about newly added information and making sure to maintain the truth consistency in knowledge baseExample - 1. All mammals have hair 2. Elephant is a mammal ‘herevore- Elephant has hair But if new statement added- Except Elephant all mammals have hair ‘herevore- Elephant has not hair Give example of Closed World Assumption? ** Open World Assumption (OWA):** OWA is an approach in knowledge representation where the system doesn't assume that everything not known is false.** Closed World Assumption (CWA):** CWA is an assumption in knowledge representation that treats everything not explicitly stated as false. It assumes the knowledge base is complete, and if a fact isn't present, it's considered untrue. Airline reservation systems: Airline reservation systems assume that all available flights are listed in the database. If a user searches for a flight from Delhi to Mumbai and the system does not find any results, the system assumes that there are no flights available on that route. What is the significance of Circumscription in Al?What do you mean by Probabilistic reasoning in Artificial intelligence? Explain with help of example. Suppose if A is true then B is true i.e A->B. But when their is a condition where we are not certain whether A is true or not then the condition is known as uncertain. Probabilistic reasoning is a way of knowledge representation where we apply the concept of probability to indicate that uncertainty in the knowledge. In probabilistic reasoning, there are two ways to solve problems with uncertain knowledge: o Bayes’ rule o Bayesian StatisticsBayesian statistics- Bayesian inference is a method of statistical inference in which Bayes' theorem is used to update the probability for a hypothesis as more evidence or information becomes available. Posterior Beliefs Evidence Prior Beliefs Example- Probabilistic reasoning in medical diagnosis helps doctors assess the likelihood of different diseases based ona patient's symptoms. It's like guessing which disease is most likely the cause, likefood poisoning, gastroenteritis, or appendicitis. This helps doctors make better decisions about the patient's care, like recommending rest or ordering tests. Describe the term uncertainty. Discuss the cause of uncertainty in real world using one scenario Uncertainty refers to the lack of complete information or knowledge about something. It is a state of mind in which an Al system is not sure about what is going to happen or what is true. Cause- 1. Limited information 2. Complexity 3. Randomness Predicting the weather:Imagine you are planning a camping trip. You have checked the weather forecast, and it says that there is a 30% chance of rain on the day of your trip. This means that there is a 70% chance of good weather, but there is still a chance that it will rain. This is an example of uncertainty. You are not sure what the weather will be like on the day of your trip, and this is causing you some anxiety. State and explain Bayes' theorem in Artificial intelligence Bayes' theorem is a mathematical principle that helps to calculate the probability of an event based on prior knowledge or information. It's particularly useful when you have new evidence andwant to update your beliefs about the likelihood of certain events. Suppose we have two events, A and B. Bayes' theorem states that the probability of A given B is equal to the probability of B given A multiplied by the prior probability of A, divided by the probability of B. _ P(BIA)- P(A) B= PB) where: e P(A|B) is the probability of event A given that event B has occurred e P(BJA) is the probability of event B given that event A has occurrede P(A) is the prior probability of event A (the probability of A before considering any new evidence) e P(B) is the probability of event B (the probability of B before considering any new evidence) For example, consider a spam filter that is trying to determine whether an email is spam or not spam. The filter can use Bayes' theorem to update its belief that the email is spam based on the presence or absence of certain keywords in the email.Define Conditional Probability Conditional probability: Conditional probability is a probability of occurring an event when another event has already happened. Let's suppose, we want to calculate the event A when event B has already occurred, “the probability of A under the conditions of B", it can be written as: P(AAB) PIA | 8) . P(B) Where P(AAB)= Joint probal ity of a and B P(B)= Marginal probability of B. If the probability of A is given and we need to find the probability of 8, then it will be given as: P(AAB) P(BIA) = =4A=) (BIA) = Fey It can be explained by using the below Venn diagram, where B is occurred event, so sample space will be reduced to set B, and now we can only calculate event A when event B is already occurred by dividing the probability of P(AAB) by P( B). Exampl In a class, there are 70% of the students who like English and 40% of the students who likes English and mathematics, and then what is the percent of students those who like English also like mathematics?Explain marginalization process The marginalization process is used to eliminate certain variables from a set of data, in order to make the data more manageable. Marginalization in probability means focusing on some variables and ignoring the rest to find the probability of the chosen ones.The process essentially involves "summing out" the variables that are not of interest, leaving only the variables that are desired. Simple Al- Simple Al, also known as narrow Al or weak Al, refers to a type of artificial intelligence that is designed to perform specific tasks. Simple Al systems are limited to a particular domain or application. They are not capable of general intelligence and cannotunderstand or reason about the world in the same way that humans do. Example- Machine learning algorithms: These algorithms are trained on large amounts of data to learn to perform specific tasks, such as image recognition or spam filtering Meta knowledge is knowledge about knowledge. It helps us to use knowledge effectively. It is the ability to understand and reason about one’s own knowledge or the knowledge of others. Example- Knowing when to trust your own judgment and when to seek out additional information: What is circumscription? Give example. Circumscription is a non-monotonicinference rule used to reason about incomplete information. It is a way of drawing conclusions from a set of premises that are not explicitly stated. Circumscription is a way of making assumptions about the world around us, even when we don't have all the information. For example, if we see a person walking down the street, we might assume that they are a human being, unless we have evidence to the contrary. What is structured knowledge? Describe examples of structured Knowledge. How Graph Search Works. Structured knowledge is a type of knowledge that is organized in a way thatis easily understood and processed by machines. It is typically stored in databases or knowledge graphs, where it can be queried and analyzed to extract insights. Structured knowledge is used in a variety of applications, including artificial intelligence, natural language processing, and search engines. Examples of structured knowledge include databases, tables, graphs, and organized lists. Examples of structured knowledge include: e Entities: Entities are objects that exist in the real world. For example, "Paris" and "France" are entities. e Relationships: Relationships are connections between entities. Forexample, the relationship between "Paris" and "France" is that Paris is the capital of France. e Facts: Facts are statements that are true or false. For example, "The capital of France is Paris" is a fact. A graph is a data structure that consists of nodes and edges. Nodes represent entities, and edges represent relationships between entities. Graph search is a technique for searching for information ina graph. Graph search algorithms work by traversing the graph, starting from a starting node and following edges until a goal node is found.There are many different graph search algorithms, but some of the most common include: e Breadth-first search: Breadth-first search explores all nodes at a given level of the graph before moving on to the next level. e Depth-first search: Depth-first search explores all nodes along a single path in the graph before backtracking and exploring another path. Discuss various features of python? How it is important in the field of artificial intelligence. 1. Simple2. OOP 3. Interpreted 4. Dynamic typing 5. Platform independent 6. Exception handling 7. Multithreading and multiprocessing In the field of artificial intelligence (Al), Python has become the language of choice for several reasons: Extensive Libraries: Python has rich libraries for Al and machine learning, such as TensorFlow, PyTorch, and scikit-learn, making it easier for developers to implement Al algorithms. Community Support: Python has a large and active community, providing support, resources, and a collaborative environment for Al research anddevelopment. Data Science Capabilities: Python's data manipulation and analysis libraries, like NumPy and Pandas, are crucial for handling large datasets, a common requirement in Al applications. Integration with Other Languages: Python can be easily integrated with languages like C and C++, allowing developers to optimize performance-critical parts of Al applications. Flexibility and Prototyping: Python's flexibility allows for quick prototyping and experimentation, which is essential in the iterative development process of Al models.What is Frame based System? What type of information frame contains? How the information is represented using frame structures? Frame-based systems are a type of knowledge representation system that uses frames to represent knowledge. A frame is a data structure that represents a stereotypical situation or concept. Frames are typically organized in a hierarchy, with more general frames at the top and more specific frames at the bottom. Frame- based systems were first developed in the 1970s They have been used in a variety of applications, including natural language processing, expert systems, and artificial intelligence. Types of Information Frames ContainAttributes: The characteristics or properties of a concept or entity. For example, a frame for a person might have slots for name, age, occupation, and education level. Relationships: The connections between concepts and entities. For instance, a frame for a person might have links to frames for their parents, siblings, and spouse. Default values: Default values are values that are assumed to be true unless they are overridden. For example, the default value for the slot "occupation" in a frame for a person might be "unemployed." Procedural attachments: Procedural attachments are code that is executedwhen a frame is used. For example, a frame for a person might have a procedural attachment that generates a description of the person. e Meta-Information: Additional information about the frame itself, such as its source, creation date, and modification history. Information in a frame is stored using a combination of slots, values, inheritance, and links. Slots: Placeholders for specific information about the concept. Values: Actual data stored within the slots. Inheritance: Mechanism for frames to inherit properties from more generalframes. Links: Connections between frames to represent relationships. Tah colmur Tacomas eae heen aos 1. Example: Person Frame Cee) Sener ECHL i eke reer oa Cure Oral 2. Hierarchical Representation: eee eM eCiLre) cece Cur Tecate eto) Centr ce | odes tne ate ta CC acess ae |Describe the functions of EasyAl. How can Easy Al be built. EasyAl is a Python library that provides a simple and easy-to-use interface for building artificial intelligence (Al) applications. It is designed for beginners and non-experts to create ai applications without requiring extensive knowledge of machine learning or deep learning. Functions of EasyAl EasyAl provides a range of functions for building Al applications, including: e Data preprocessing: EasyAl provides tools for cleaning, normalizing, and transforming data, which is essential for training Al models.¢ Model training: EasyAl supports various machine learning algorithms, including classification, regression, and clustering. It provides a simple interface for training models on your data. ¢ Model evaluation: EasyAl offers tools for evaluating the performance of trained models on new data, allowing you to assess their accuracy and generalization ability. e Model deployment: EasyAl simplifies the process of deploying trained models into real-world applications, enabling you to use your models to make predictions or decisions.Building EasyAl from Scratch If you have a strong understanding of Python programming, machine learning, and software engineering, you can build EasyAl from scratch. This involves developing a comprehensive Python library that encapsulates the data preprocessing, model training, model evaluation, and model deployment functions mentioned earlier. Building EasyAl can be accomplished in various ways, ranging from building it from scratch to utilizing existing libraries and contributing to the open-source project. The most suitable approach depends on your expertise and the desired functionality of your Al application.‘An associative network is a type Cee ae ec ey Pinter rele ena Catered OER ee eae uns atest Peeler Rau Rain) Ea Se na Een ac ORC) De eae Rec aL) the connections (associations) Deer aCe Eten oem eect Ce Rc oe Ce aa Ree ete ete SP te or Le Dee SuSE Reels CEU Peete ls Cen ene Cer CU represent relationships or Pee er ee sea corresponding concepts. These ee RC et Re) ne eas Dec ee Tel tere CeCe De Cer Cn Eins eae grate Ce aC oe acer Dene) PU Sine eT Lar) TSE Eel et Ree re ec terete Ce CMR Co) Sn Teter Remon) Peete RaeWhat is "Dempster - Shafter Theory". What is the relation between Belief and Plausibility in Dempster- Shafter Theory DST is an evidence theory, it combines all possible outcomes of the problem. Hence it is used to solve problems where there may be a chance that a different evidence will lead to some different result. DST is a mathematical theory of evidence based on belief functions and plausible reasoning. It is used to combine separate pieces of information (evidence) to calculate the probability of an event. DST offers an alternative for the mathematical representation of uncertainty. In DST, belief and plausibility are two important measures of the degree to which an event is believed to be true.Example: Let us consider a room where four people are present, A, B, C, and D. Suddenly the lights go out and when the lights come back, B has been stabbed in the back by a knife, leading to his death. No one came into the room and no one left the room. We know that B has not committed suicide. Now we have to find out who the murderer is. To solve these there are the following possibilities: Either {A} or {C} or {D} has killed him. Either {A, C} or {C, D} or {A, D} have killed him. * Or the three of them have killed him i.e; {A, C, D} * None of them have killed him {0} (let's say). There will be possible evidence by which we can find the murderer by the measure of plausibility. Using the above example we can say: Set of possible conclusion (P): {p1, p2....pn} where P is a set of possible conclusions and cannot be exhaustive, i.e. at least one (p) | must be true.¢ Belief is a measure of how strongly we believe a proposition is true. It is denoted by Bel(A), where A is the proposition of interest. Bel(A) ranges from 0 to 1, where 0 indicates no belief in A, and 1 indicates complete belief in A. e Plausibility is a measure of the degree to which a proposition is possible. It is denoted by PI(A). PI(A) also ranges from 0 to 1, where 0 indicates that A is impossible, and 1 indicates that A is possible. The relationship between belief and plausibility is given by the following equation: O <= Bel(A) < PI(A) < 1This means that belief is always less than or equal to plausibility. The difference between belief and plausibility represents the amount of uncertainty about the proposition. In Dempster-Shafer (DS) theory, a high difference between belief and plausibility indicates a high degree of uncertainty about a proposition. This means that there is a significant amount of evidence both for and against the proposition, and it is difficult to say with certainty whether or not the proposition is true.