Artificial Intelligence

AI

AI is branch of computer science by which we can create intelligent machine which can behave like a human, think like humans and able to make decisions.

Examples

  1. Chatbots use AI to understand customer problems faster and provide more efficient answers
  2. Intelligent assistants use AI to parse critical information from large free-text datasets to improve scheduling
  3. Recommendation engines can provide automated recommendations for TV shows based on users’ viewing habits

Goals of AI

  1. Replicate Human Intelligence
  2. Solve Knowledge-Intensive tasks
  3. An Intelligent Connection of perception and action
  4. Building a machine which can perform tasks that requires human intelligence such as
    • Providing a theorem
    • Playing Chess
    • Plan some surgical operation
    • Driving a car in traffic

What is Intelligent Components in AI?

AI has focused on the following components of intelligence:

learning, reasoning, problem solving, perception, and linguistic intelligence

AI Intelligence Components

Agents in AI

What is an Agent?

An agent can be anything that perceive environment through sensors & act upon that environment through actuators.

Three types of agents:

  1. Human Agent -> Eyes, Ears & other organs which work for sensors
  2. Robotic Agent -> Cameras, Infrared Range Finder
  3. Software Agent -> Key Strokes

Types of AI Agents:

Agents can be grouped into five classes based on their degree of perceived intelligence & capacity.

  1. Simple Reflex Agent
  2. Model-based reflex agent
  3. Goal based agents
  4. Utility based agents
  5. Learning Agents

1. Simple Reflex Agent

  • This agent works only on the basis of current perception
  • It does not bother about the previous state in which the system was.
  • This type of agent is based upon the condition-action rule. If condition is true then action is taken else not.

Problem Faced in Simple Reflex Agent

  1. Very Limited Intelligence
  2. No knowledge about the non-perceptional parts of the state
  3. operating in a partially observable environment, infinite loops are unavailable

2. Model based Reflex Agent

  • It works by finding a rule whose condition matches the current situation
  • It can handle partially observable environment
  • Updating the state requires information about
    • how world evolves independently from the agent
    • how the agent actions affect the world

3. Goal Based Agents

  • It focus only on reaching the goal set and hence the decision took by the agent is based on how far it is currently from their goal of desired state.
  • Every action is intended to minimize their distance from the goal
  • Decision Making skill by choosing the right from the various options available
  • more flexible

4. Utility based Agents

  • Similar to goal based agent
  • it act based not only goals but also the best way to achieve the goal

5. Learning Agent

It can learn from its past experience or it has a learning capabilities

4 Conceptual Components

  1. Learning element
  2. Critic
  3. Performance Element
  4. Problem Generates
Leave a Reply 0

Your email address will not be published. Required fields are marked *


Exit mobile version