Successfully reported this slideshow.
Your SlideShare is downloading. ×

AI.ppt

Ad
Ad
Ad
Ad
Ad
Ad
Ad
Ad
Ad
Ad
Ad
Loading in …3
×

Check these out next

1 of 13 Ad

More Related Content

Similar to AI.ppt (20)

Recently uploaded (20)

Advertisement

AI.ppt

  1. 1. What is Artificial Intelligence? • AI is the effort to develop systems that can behave/act like humans. • Turing Test • The problem = unrestricted domains – human intelligence vastly complex and broad – associations, metaphors, and analogies – common sense – conceptual frameworks
  2. 2. Elements of AI • Natural Language Processing • Robotics • Perceptive Systems (Vision) • Expert Systems
  3. 3. How are Machines Intelligent? • Constrained Heuristic Search – How do you play chess? • first move = 20 possible • second move = 400 possible • 7th move = 1,280,000,000 possible – Depth First vs. Breath First Searching – Ability to Learn
  4. 4. Decision Tree
  5. 5. Depth First Search
  6. 6. Breath First Search
  7. 7. Expert Systems • Capture knowledge of an expert. • Represent Knowledge as a – rule base • if then rules – semantic net • hierarchy – frames • shared characteristics, IS-A relationships
  8. 8. Expert System Successes • XCON - configures systems for DEC • Prospector - an mining expert • MYCIN - infectious blood diseases • EMYCIN - Empty MYCIN
  9. 9. Elements of Expert System Shell • Knowledge Base – rules • Working Memory – facts of current case • Inference Engine – applies rules using current set of facts • Explanation Facility • CLIPS
  10. 10. Neural Networks & The Brain • Base on architecture of human brain – Neurons connected by axons & dendrites – 100 billion neurons – 1,000 dendrites per neuron – 100,000 billion synapses – 10 million billion interconnectons per second
  11. 11. How a Neuron Works Impulses come from other neurons. When sum of inputs reaches a threshold, neuron fires. Sending impulses to next level of neurons.
  12. 12. An Artificial Neural Network Inputs Hidden Output w w w w w w
  13. 13. Neural Networks, NN • NNs learn by using a training set and adjusting the weights on each connection. • NNs do not have to be “told” explicit relationship rules. • NNs can work with partial inputs. • NNs cannot explain their results. • NNs can take a long time to train. • A NN demonstration

×