Introduction to Artificial Intelligence PDF

EG1004 Artificial Intelligence for Beginners Ms. May Me Moon Zin Educational Background B.E(Information Science and Technology), UTYCC Master Candidate, Mandalay Technological University (COE) Master Candidate, Chiang Mai University Introduction to Artificial Intell...

EG1004 Artificial Intelligence for Beginners Ms. May Me Moon Zin Educational Background B.E(Information Science and Technology), UTYCC Master Candidate, Mandalay Technological University (COE) Master Candidate, Chiang Mai University Introduction to Artificial Intelligence What is Artificial Intelligence? It is a technique which enables systems to mimic human behavior. It refers to computer systems capable of performing complex tasks that historically only a human could do, such as reasoning, making decisions, or solving problems. AI is an umbrella term that encompasses a wide variety of technologies, including machine learning, deep learning, and natural language processing (NLP).  HISTORY OF AI ▪ The term "Artificial Intelligence" first adopted by American Computer scientist John McCarthy at the Dartmouth Conference. ▪ The period from 1956 to 1974 is commonly known as the "Golden Age" of artificial intelligence (AI). ▪ Between 1993 and 2011, there were significant leaps forward in artificial intelligence (AI), particularly in the development of intelligent computer programs. ▪ From 2011 to the present moment, significant advancements have unfolded within the artificial intelligence (AI) domain. Why AI important? ▪ AI Analyzes Data Quickly: AI can process and analyze vast amounts of data faster than humans. ▪ AI Provides Accurate Predictions: AI uses data to forecast outcomes with high precision. ▪ AI Personalizes Experiences: AI tailors recommendations based on individual preferences. ▪ AI Supports Better Decisions: AI offers data-driven insights to make informed choices. ▪ With the help of AI, you can create such software or devices which can solve real-world problems very easily and with accuracy such as health issues, marketing, traffic issues, etc. ▪ You can also create your personal virtual Assistant, such as Cortana, Google Assistant, Siri, etc. ▪ AI opens a path for other new technologies, new devices, and new Opportunities. Examples of AI in everyday life ChatGPT: Uses large language Google Translate: Uses deep models (LLMs) to generate text in learning algorithms to translate response to questions or text from one language to comments posed to it. another. Netflix: Uses machine learning algorithms to create personalized Tesla: Uses computer vision to recommendation engines for power self-driving features on users based on their previous their cars. viewing history.  ▪ Narrow AI (Weak AI): AI designed to perform a specific task, such as Memorize!!! facial recognition or virtual assistants like Siri and Alexa. It cannot perform tasks beyond its programmed function. ▪ General AI (AGI - Artificial General Intelligence): AI that can understand, learn, and apply intelligence across a wide range of tasks, similar to human intelligence. This type of AI is theoretical and has not yet been developed. Types of ▪ Superintelligent AI: A hypothetical AI that surpasses human Artificial intelligence in every aspect, including creativity, problem-solving, Intelligence and decision-making. This form of AI is speculative and not yet realized. Group Discussion: "If You Could Create an AI, What Would It Do?" Guiding Questions: ✓ What problem would your AI solve? ✓ Would it be a virtual assistant, a robot, or something else? ✓ How would people interact with it? ✓ What features would make it smart and useful? What are Intelligent Agents? An intelligent agent is a program that can make decisions or perform a service based on its environment, user input and experiences. These programs can be used to autonomously gather information on a regular, programmed schedule or when prompted by the user in real time. The key Components of an Intelligent Agent: Perception (Sensors): The agent perceives its environment through sensors. These sensors could be physical, like cameras or microphones, or virtual, like input from a website or software. Decision-Making: After perceiving the environment, the agent processes the information, analyzes it, and decides the best course of action to take. This step often involves algorithms, including machine learning or rule-based systems, to help the agent make decisions. Actions (Effectors/Actuators): Once the decision is made, the agent takes action. The action could be moving a robotic arm, sending a message, or updating a software process. Examples: A virtual assistant like Siri or Alexa, A robot vacuum cleaner Four main rules for AI Agent Memorize!!! ▪ Rule 1: An AI agent must have the ability to perceive the environment. ▪ Rule 2: The observation must be used to make decisions. ▪ Rule 3: Decision should result in an action. ▪ Rule 4: The action taken by an AI agent must be a rational action. Components of Intelligent Agents Sensors (Perception): Function: Gather information from the environment. Examples: Cameras, microphones, GPS, temperature sensors. Actuators (Action): Function: Execute actions to influence the environment. Examples: Motors, speakers, displays, robotic arms. Decision-Making (Processing): Function: Analyze data, make choices, and determine the best course of action. Examples: Algorithms, decision trees, machine learning models. Learning Mechanism (Adaptation): Function: Improve performance over time by learning from past experiences. Examples: Reinforcement learning, supervised learning, neural networks. PEAS Representation Memorize!!! P: Performance measure Performance: Safety, time, legal drive, comfort E: Environment Environment: Roads, other vehicles, road signs, pedestrian A: Actuators Actuators: Steering, accelerator, brake, signal, horn S: Sensors Sensors: Camera, GPS, speedometer, odometer, accelerometer, sonar. Common Types of Intelligent Agents Memorize some names!!! Simple Reflex Agents: react directly to specific inputs using set rules. Example: A smoke detector that sounds an alarm when it detects smoke. Model-Based Agents: use an internal model to understand and react to the environment. Example: A robot that uses a map to navigate through a room. Goal-Based Agents: make decisions to achieve specific goals. Example: A GPS navigation system that finds the best route to your destination. Utility-Based Agents: choose actions to maximize overall satisfaction or benefit. Example: A movie recommendation system that suggests films based on your preferences. Group Discussion: “Applying PEAS Representation to AI Agents” (Smart virtual assistant like Siri, Autonomous Vacuum Cleaner)