Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

KAIST 2012 Fall 전자공학개론 6조 발표 PPT

678 views

Published on

KAIST 2012 Fall 전자공학개론 6조 발표 PPT

  • Be the first to comment

KAIST 2012 Fall 전자공학개론 6조 발표 PPT

  1. 1. Artificial Neural Network EE105 6조
  2. 2. Artificial Neural Network (ANN)• A mathematical model inspired by biological neural networks• ANN consists of an interconnected group of artificial neurons ▶
  3. 3. Compare to Brain Biological Neural Network Artificial Neural Network Neuron Unit (or node) Synapse ConnectionInhibition or Excitation of Neuron Connection Weight Threshold of firing rate Activation Function
  4. 4. ANN Structure ANN BNNInput Layer Sensory NeuronsHidden Layer InterneuronsOutput Layer Motoneurons
  5. 5. Attractions of ANN Model• Learning – Human brain can learn by changing their interconnections between neurons – ANN can learn by changing their connection weights between units• Parallel Processing : Many processes simultaneously• Robustness: It works even if it is damaged
  6. 6. How to Work?Unit 1 UnitUnit 2 Unit …Unit Unit n
  7. 7. Example – AND Operator Unit 1 Unit 3 Unit 2 X f(X) Y 0 0 0 0 0 0 1 0.5 0.5 0 1 0 0.5 0.5 0 1 1 1 1 1
  8. 8. Example – OR OperatorUnit 1 Unit 3Unit 2 X f(X) Y0 0 0 0 00 1 0.5 0.5 11 0 0.5 0.5 11 1 1 1 1
  9. 9. Example – XOR OperatorUnit Unit 1 3 Unit 5Unit Unit 2 4 Unit 1 Unit 2 Unit 5 X f(X) Y 0 0 0 0 0 0 1 0.5 0.5 1 1 0 0.5 0.5 1 1 1 0 0 0
  10. 10. How to Learn?1. Set all connection weight as randomly2. Input the data3. If the output corrects (expected value) ▷ Then, exit iteration ▷ Else, change the connection weights to reduce difference and repeat (go to 2)How to change connection weight?There are many algorithms but is hard to explain because of themargin of the slide is too small!!
  11. 11. Applications• Pattern Recognition – Voice Recognition – Medical Treatment (e.g. cancer detect)• Data Processing – Noise Filtering• Robotics – Data-Driven Predictive Controller
  12. 12. Any Questions? Thank you

×