intro to AI

• Artificial Intelligence (AI)


  An entity (or collective set of cooperative entities), able to receive inputs from the environment, interpret and learn from such inputs, and exhibit related and flexible behaviors and actions that help the entity achieve a particular goal or objective over a period of time

  
• Artificial Intelligence (AI)


  A wide-ranging branch of computer science concerned with building smart machines capable of performing tasks that typically require human intelligence. AI is an interdisciplinary science with multiple approaches, but advancements in machine learning and deep learning are creating a paradigm shift in virtually every sector of the tech industry
• Artificial Intelligence (AI)


  The capability of a computer to imitate intelligent human behavior. Through AI, machines can analyze images, comprehend speech, interact in natural ways, and make predictions using data

  
• There is a close connection and overlap among the fields of machine learning, AI, and deep learning
• AI


  The quest for developing non-biological systems that exhibit human-like forms of intelligence
• Early and promising approaches to AI included symbolic models and reasoning, early versions of neural networks, and expert systems
• Reasons to study AI

  • Making machines think like humans
  • Simulating the human thinking process and problem-solving
• Cognitive Modelling


  1. Understand how humans solve problems

  2. Turn mental processes into a software model

  3. Simulate human behaviour
• AI development milestones


  • Maturation of AI (1943-1952)
  • Birth of AI (1952-1956)
  • The golden years-Early enthusiasm (1956-1974)
  • The first AI winter (1974-1980)
  • A boom of AI (1980-1987)
  • The second AI winter (1987-1993)
  • The emergence of intelligent agents (1993-2011)
  • Deep learning, big data and artificial general intelligence (2011-present)

  
• Types of AI (based on capabilities)

  • Artificial Narrow Intelligence (ANI)
  • Artificial General Intelligence (AGI)
  • Artificial Super Intelligence (ASI)
• Artificial Narrow Intelligence (ANI)


  Also known as Weak AI, machines that can perform only a narrowly defined set of specific tasks without any thinking ability
• Artificial General Intelligence (AGI)


  Also known as Strong AI, machines that possess the ability to think and make decisions like humans
• Artificial Super Intelligence (ASI)


  The hypothetical stage where the capability of computers will surpass human beings
• Types of AI (based on functionality)

  • Reactive Machines AI
  • Limited Memory AI
  • Theory of Mind AI
  • Self-aware AI
• Reactive Machine AI


  Machines that operate solely based on the present data, taking into account only the current situation without forming inferences
• Limited Memory AI


  Can make informed and improved decisions by studying the past data from its memory
• Theory of Mind AI

  Focuses mainly on emotional intelligence so that human beliefs and thoughts can be better comprehended
• Self-Aware AI


  Machines that have their own consciousness and become self-aware
• Theory of Mind AI

  A more advanced type of Artificial Intelligence that is speculated to play a major role in psychology and focus mainly on emotional intelligence so that human beliefs and thoughts can be better comprehended

  
• The Theory of Mind AI has not yet been fully developed but rigorous research is happening in this area
• Self-Aware AI


  A type of AI where machines have their own consciousness and become self-aware, which is a little far fetched given the present circumstances but achieving a stage of superintelligence might be possible in the future
• Geniuses like Elon Musk and Stephen Hawkings have consistently warned us about the evolution of AI
• Branches of Artificial Intelligence

  • Machine Learning
  • Deep Learning
  • Natural Language Processing
  • Robotics
  • Expert Systems
  • Fuzzy Logic

  
• Machine Learning


  The science of getting machines to interpret, process and analyze data in order to solve real-world problems, with three categories: supervised learning, unsupervised learning, and reinforcement learning
• Deep Learning


  The process of implementing Neural Networks on high dimensional data to gain insights and form solutions, an advanced field of machine learning that can be used to solve more advanced problems
• Natural Language Processing (NLP)

  The science of drawing insights from natural human language to communicate with machines and grow businesses, used for filtering terroristic language, understanding customer reviews, and providing recommended answers
• Robotics


  A branch of Artificial Intelligence which focuses on different branches and application of robots, with AI robots being artificial agents acting in a real-world environment to produce results by taking accountable actions
• Fuzzy Logic


  A computing approach based on the principles of "degrees of truth" instead of the usual modern computer logic i.e. boolean in nature, used in medical fields, automatic gearboxes, and vehicle environment control
• Expert Systems


  An AI-based computer system that learns and reciprocates the decision-making ability of a human expert, using if-then logical notations to solve complex problems, used in information management, medical facilities, loan analysis, and virus detection
• Turing Test


  A test proposed by Alan Turing to define intelligence, where a machine needs to communicate through a text interface and trick an interrogator into thinking the answers are coming from a human, requiring natural language processing, knowledge representation, reasoning, and machine learning
• Rational Agent


  An agent that takes actions to achieve its goals by observing a set of rules and following their logical implications in order to achieve a desirable outcome, with the performance measure depending on the degree of success in completing the task
• General Problem Solver (GPS)


  An early AI program intended to solve any general problem using the same base algorithm, able to solve well-defined problems like proving mathematical theorems and solving word puzzles, but intractable for real-world problems due to the number of possible paths
• Intelligent Agent


  An agent that uses techniques like machine learning, stored knowledge, and rules to interact with its environment, with the learning model built using machine learning and the inference engine taking decisions based on the model
• Machine learning is used in many applications like image recognition, robotics, speech recognition, and predicting stock market behavior