In this module, you will get introduced to the different terms related to problem-solving in artificial intelligence and the steps for solving problems. You will gain insights into the significance of production systems, their components, and their main features. Further, through the examples of artificial intelligence problems, you will be able to understand the role of artificial intelligence in developing intelligent machines to solve real-world problems. The module will also describe the different categories of problems based on their nature in detail.

This assessment is a graded quiz based on the modules covered in this week.

In this module, you will learn about the basic concepts of search problems, search trees, search processes, search types, and the criteria for evaluating search strategies. The module will also cover the algorithm of four uninformed search techniques. You will get introduced to breadth-first search and depth-first search techniques along with their applications. Further, you will gain insights into the iterative deepening and bidirectional search techniques along with their advantages and disadvantages.

In this module, you will learn about the informed search techniques used in artificial intelligence. Informed search techniques follow a guided process towards achieving a known goal, hence they are also referred to as guided search or heuristic search. You will also study heuristic knowledge and heuristic function. Further, you will get introduced to different informed search techniques and learn the key features of those techniques.

In this module, you will understand the need and significance of knowledge representation and its associated concepts. You will learn about different types of knowledge involved in artificial intelligence. You will also comprehend how knowledge is acquired, created, and stored in different scenarios. The module will also cover the organization of knowledge. Further, you will gain insights into the knowledge management concepts and knowledge engineering principles and practices.

In this module, you will understand the concept of logic, a formal language used to represent knowledge and facts. There are two kinds of logic in the field of AI: propositional logic and predicate logic. These are the most widely used knowledge representation techniques. These methods are used to represent real-world facts in the form of language, which uses words, phrases, and sentences to represent and reason about properties and relationships in the world. You will study these methods in detail in this module.

This assessment is a graded quiz based on the modules covered in this week.

In this module, you will learn about the problems in artificial intelligence which are solved using game-playing strategies. You will learn how game-playing aids decision-makers. You will also understand the concept of adversarial search and different types of games. Further, you will gain knowledge about approaching a game through min-max strategy. Finally, you will learn about how to solve a game using the alpha-beta pruning strategy.

In this module, you will learn about the concepts of reasoning with uncertainty, sources of uncertainties, and representation of uncertain knowledge. It also includes various types of reasoning such as monotonic, non-monotonic, and probabilistic reasoning. You will gain insights about them through the examples which clarify the intricate concepts of reasonings and how they are handled.

This assessment is a graded quiz based on the modules covered in this week.

In this module, you will understand the definition, history, and concepts of Natural Language Processing (NLP). NLP is the part of artificial intelligence that studies how humans establish communication with machines. You will learn about the phases of NLP and the challenges encountered in the process of NLP. Further, you will gain insights into different parsing techniques. Also, you will learn about transition networks in NLP.

In this module, you will learn about the concept of learning and planning in the field of AI. Every intelligent system needs to possess some form or degree of understanding. Planning is important since all the actions required to solve a problem need to be planned before their application for the desired result. All these aspects will be delved into in this module. You will also study some important learning algorithms namely, genetic algorithms, neural networks, and decision trees.

In this module, we will discuss the concept of classification in machine learning. Classification algorithms are used to classify ideas and objects into pre-set categories or sub-populations. Using various pre-categorized training datasets, the classification algorithms group future datasets into categories. The study of classification in the machine learning domain is vast. You will learn three major classification algorithms namely Naïve Bayes, support vector machines, and K-means clustering. Further, you will also learn briefly about a reasoning algorithm based on fuzzy logic.

The primary aim of artificial intelligence is to develop expert systems for solving real-world problems, effectively and economically. Expert systems are nothing but intelligent systems working in a limited domain. In this module, various issues related to the development of expert systems are presented.

This assessment is a graded quiz based on the modules covered in this week.

Course Wrap- Up