artificial intelligence introduction slides
Download as PPTX, PDF0 likes14 views
ARTIFICIAL INTELLEGENCE
artificial intelligence introduction slides
- 2. Topic for today Characteristics of AI Components of AI AI Approaches Current Trends in AI Intelligent Agents
- 3. Characteristics of AI • Symbolic Processing • Non-algorithmic Processing • Reasoning • Perception • Communication • Ability to Learn • Imprecise knowledge • Planning • Fast decision making
- 4. • Symbolic Processing • In AI applications, computers process symbols rather than numbers or letters. • AI Applications process strings of characters that represent real-world entities or concepts. • Symbols can be arranged in structures such as lists, hierarchies, or networks. These structures show how symbols relate to each other.
- 5. • Non-algorithmic Processing • Computer programs outside the AI domain are programmed algorithms; that is, fully specified step-by step procedures that define a solution to the problem. The actions of a knowledge-based AI system depend to a far greater degree on the situation where it is used.
- 6. Reasoning is the ability to solve problems through logical deduction Perception is the ability to deduce things about the world from visual images, sounds and other sensory inputs. It involves deducing things about the world from visual images, sounds and other sensory inputs. Communication is the ability to understand written and spoken language. It involves the ability to communicate in human language, understanding people’s intentions
- 7. 7. Imprecise knowledge An AI program needs an imprecise or general knowledge whereas a conventional program needs a precise or specific knowledge.
- 8. Planning is the ability to set and achieve goals. It involves setting and achieving goals through sequences of actions. Sequences of actions can be undertaken that will affect progress towards achieving the goals. 8. Planning
- 9. 9. Fast decision making • Al has a powerful role to play in making real-world decisions. • Even many of the most innovative organizations in the world such as Facebook, Google and Amazon rely on depend on AI algorithms for decision making .
- 10. Components of AI
- 11. Learning One of the essential components of ai, learning for AI includes the trial- and-error method. The solution keeps on solving problems until it comes across the right results. This way, the program keeps a note of all the moves that gave positive results and stores it in its database to use the next time the computer is given the same problem.
- 12. Reasoning • To reason is to allow the platform to draw inferences that fit with the provided situation. • Further, these inferences are also categorized as either inductive or deductive. • Inductive reasoning involves starting from specific premises and forming a general conclusion, while deductive reasoning involves using general premises to form a specific conclusion
- 13. Problem solving • The problem-solving component in AI allows the programs to include step- by-step reduction of difference, given between any goal state and current state.
- 14. Perception • The processes are maintained internally and allow the perceiver to analyze other scenes in suggested objects and understand their relationship and features.
- 15. Language- understanding • AI is developed in a manner that it can easily understand the commonly used human language, English. • This way, the platform allows the computers to understand the different computer programs executed over them easily.
- 16. AI Approaches 1. Acting humanly- When a computer acts perfectly like a human being, and it is difficult to differentiate between two by using technologies such as natural language processing, automated reasoning, machine learning and automated reasoning. T he Turing test, called an imitation game, determines whether a machine can demonstrate human intelligence or not without any physical contact.
- 17. • 2. Thinking humanly – When a computer thinks just as a human and performs tasks usually performed with human intelligence such as driving a car. • The method to determine how humans think, cognitive modeling approach is used based on three techniques- Introspection, Psychological testing, and Brain imaging.
- 18. • 3. Thinking Rationally -A person is considered rational (reasonable, sensible, and with a good sense of judgment) and the computer thinks rationally as per the recorded behavior and solves problems logically. In other words, • the solving of a specific problem is quite different from solving it in practice and computers take help of that rational thought to perform.
- 19. • 4. Acting Rationally- The study of how humans act in uncertainty or complexity relies completely on rational agents. • Actions depend on conditions, environmental factors, and existing data to maximize the expected value of its performance. • It normally relies on black-box or engineering approach to successfully accomplish the goal.
- 20. Current Trends in Artificial Intelligence GENERATIVE AI ETHICAL AI AUGMENTED AI SUSTAINABLE AI SHADOW AI MULTIMODAL AI
- 21. Intelligent Agents • AI agents are software programs or systems that are designed to perceive their environment, make decisions, and take actions autonomously to achieve specific goals. These AI systems can be used in various applications such as chatbots, robotics, personal assistants, and more.
- 22. Agents • An agent can be anything that perceive its environment through sensors and act upon that environment through actuators. • An Agent runs in the cycle of perceiving, thinking, and acting AGENT=HARDWARE + SOFTWARE • Agent is designed to interact with some environment, and it has some predefined goals for environment • Agent perceives the environment, decide action to be taken and takes the action until the goal state is reached/achieved • Example: Self driving car • Agent: Self driving car • Environment: roads, signals and traffic • Actuators: gears, horn, indicators, clutch, breaks, accelerator etc. • Goal: reaching destination safely and comfortably with minimum time
- 23. Agents • An agent can be anything that perceive its environment through sensors and act upon that environment through actuators. • An Agent runs in the cycle of perceiving, thinking, and acting AGENT=HARDWARE + SOFTWARE • Agent is designed to interact with some environment, and it has some predefined goals for environment • Agent perceives the environment, decide action to be taken and takes the action until the goal state is reached/achieved • Example: Self driving car • Agent: Self driving car • Environment: roads, signals and traffic • Actuators: gears, horn, indicators, clutch, breaks, accelerator etc. • Goal: reaching destination safely and comfortably with minimum time
- 24. Agents An agent can be: • Human-Agent: Sensors : Eyes, Ears & Other Organs. Actuators : Hand, Legs, Vocal tract. • Robotic Agent: Sensors : Cameras, Infrared range finder, NLP Actuators : Various motors • Software Agent: Sensors : Keystrokes, File contents, network packets Actuators : Screen, writing files, and sending network packets An intelligent agent is an autonomous entity which act upon an environment using sensors and actuators for achieving goals.
- 25. Agent Sensor: It detects the change in the environment and sends the information to other electronic devices. An agent observes its environment through sensors. Actuators: These are component of machines that converts energy into motion. The actuators are only responsible for moving and controlling a system. Effectors: These are devices which affect the environment. Effectors can be legs, wheels, arms, fingers, wings, fins, and display screen.
- 26. Intelligent Agents: Following are the main four rules for an AI agent: 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
- 27. Rational Agent A rational agent is an agent which has clear preference, models uncertainty, and acts in a way to maximize its performance measure with all possible actions. A rational agent is said to perform the right things. AI is about creating rational agents to use for game theory and decision theory for various real-world scenarios. For an AI agent, the rational action is most important because in AI reinforcement learning algorithm, for each best possible action, agent gets the positive reward and for each wrong action, an agent gets a negative reward.
- 28. Rationality: The rationality of an agent is measured by its performance measure. Rationality can be judged on the basis of following points: • Performance measure which defines the success criterion. • Agent prior knowledge of its environment. • Best possible actions that an agent can perform. • The sequence of percepts.
- 29. Structure of an AI Agent • The task of AI is to design an agent program which implements the agent function. • The structure of an intelligent agent is a combination of architecture and agent program. • It can be viewed as: Agent = Architecture + Agent program (H/W) (S/W) Main three terms involved in the structure of an AI agent: • Architecture: Architecture is machinery that an AI agent executes on. • Agent Function: Agent function is used to map a percept to an action. f : P* A → The agent function for an agent specifies the action taken by the agent in response to any percept sequence • Agent program: Agent program is an implementation of agent function. An agent program executes on the physical architecture to produce function f.
- 30. Structure of an AI Agent • Main three terms involved in the structure of an AI agent: • Architecture: Architecture is machinery that an AI agent executes on. • Percept Sequence: Complete history of environment that agent has perceived • Agent Function: Mapping of percept sequence to an action (Agent function is used to map a percept to an action) f : P* A → • Agent program: Agent program is an implementation of agent function. An agent program executes (embedded) on the physical architecture to produce function f. Agent programs take the current percept as input from the sensors and return an action to the actuators The agent function is an abstract mathematical description; the agent program is a concrete implementation, running within some physical system.
- 31. • The performance measure evaluates the behavior of the agent in an environment. A rational agent acts so as to maximize the expected value of the performance measure, given the percept sequence it has seen so far.