[Artificial Intelligence] Introduction to Aritificial Intelligence

“Artificial Intelligence is concerned with intelligent behavior in artifacts. Intelligent behavior involves perception, reasoning, learning, communication, and acting in complex environments.” by Nilsson

“AI has one of its long-term goal the development of machines that can do these things as well as humans can, or possibly even better.” by Nilsson

The Turing Test

“Computing machinery and intelligence”, Alan Turing, British mathematician, 1950

• Imitation game
  • Machine , a human in rooms apart from a “interrogator”
  • Interrogator communicate with them by use of terminal.
  • Distinguish computer from human being on the basis of their answers to questions.
  • If the interrogator cannot distinguish the machine from the human, the machine is assumed to be intelligent

---

• The 65-year-old Turing Test is successfully passed if a computer is mistaken for a human more than 30% of the time during a series of five-minute keyboard conversations.
• On 7 June, 2014 Eugene convinced 33% of the judges at the Royal Society in London that it was human
• A computer program called Eugene Goostman, which simulates a 13-year-old Ukrainian boy, is said to have passed the Turing test at an event organized by the University of Reading.
• Ex) How mutch wood ewe pay 4 a pear of shews?

Eugene Goostman

Ray Kurzweil conversation with Eugene Goostman

Question > How old are you?
Eugene: I’m a little boy. 13 years old.
Question > How much is two plus two?
Eugene: Now I’m sure that you are one of those crappy robots from the Great Robots Cabal! And I know your password: 2 + 2=4.0! Now divide by zero and die!!!!
Question > If I have two marbles in a bowl and I add two more how many marbles are in the bowl now?
Eugene: Not too many. But I can’t tell you the exact number, I forgot it. If I’m not mistaken –you still didn’t tell me where you live. OR it’s a secret?:-)
Question > I live in the capital of the United States. Do you know where that is?
Eugene: Every nerd knows that the capital of The United States is Washington.
Question > I live in the capital of the country that put a man on the moon.
Eugene: Well, if you want it, the capital of The United States is Washington.
Question > I live in the capital of the country that built the great wall.
Eugene > Tell me more about Capital. I like to learn about different places!

Approaches to Artificial Intelligence

• Symbol Processing Approaches
• Subsymbolic Approaches

Symbol Processing Approaches

• Physical Symbol System Hypothesis: Newell and Simon
  • Physical Symbol System has the necessary and sufficient means for general intelligent action.
• Physical Symbol System: machine capable of manipulating symbolic data-adding numbers, rearranging lists of symbols, replacing some symbols of others.
• Declarative knowledge base(first order logic)
• Logical operations(logical reasoning to deduce consequences of knowledge)
• Real Problem - requires substantial knowledge of the domain - called a Knowledge based approach.
• LISt oriented Programming language(LISP)

Subsymbolic Approaches

• Processing of Signals not symbols
• Recognition of familiar faces
  • Treating images as multidimesional signals not as symbols
• Bottom up approach
  • Lowest level: duplicating signal processing abilities and control systems of simpler animals-insects
  • Proceed in steps up the evolutionary ladder
• Neural Networks inspired by biological models
• Interesting for their ability to learn.
• Interconnected Networks of Simple Units => (connectionism)

Neural Network

• Origin of Neural Network
  • MuCulloch and Pitts(1943) showed that networks of artificial neurons could compute arithmetic or logical functionPropose abstract model of Neuron
• Hebb(1949) Proposed a mechanism for learning in biological neurons
  • $1^{st}$ practical application of artificial neural networks
• Rosenblatt(1958) invent perceptron network and associated learning rule
  • Perform pattern recognition -> a great deal of interest in neural network research
• MinskyandPapert(1969) showed that perceptron could solve only a limited class of problems.
  • for a decade neural network research was suspended.
  • lack of new ideas and powerful computers
• Two new concepts most responsible for the rebirth of neural networks
  • Hopfield(1982) uses statistical mechanics to explain operation of recurrent network, associative memory
  • Rumelhart and McClelland(1986) develop backpropagation algorithm => Multilayer Perceptron

History of Artificial Neural Networks

• McCulloch and Pitts (1943): first neural network model
• Hebb (1949): proposed a mechanism for learning, as increasing the synaptic weight between two neurons, by repeated activation of one neuron by the other across that synapse (lacked the inhibitory connection)
• Rosenblatt (1958): Perceptron network and the associated learning rule
• Widrow & Hoff (1960): a new learning algorithm for linear neural networks (ADALINE)
• Minsky and Papert (1969): widely influential book about the limitations of single-layer perceptrons, causing the research on NNs mostly to come to an end.
• Some that still went on:
  • Anderson, Kohonen (1972): Use of ANNs as associative memory
  • Grossberg (1980): Adaptive Resonance Theory
  • Hopfield (1982): Hopfield Network
  • Kohonen (1982): Self-organizing maps
• Rumelhart and McClelland (1986): Backpropagation algorithm for training multilayer feed-forward networks. Started a resurgence on NN research again.
• SVM(Support Vector machine)
• DeepLearning