1 / 13

Back-propagation

Back-propagation. Chih-yun Lin 6/6/2014. Agenda. Perceptron vs. back-propagation network Network structure Learning rule Why a hidden layer? An example: Jets or Sharks Conclusions. Network Structure – Perceptron. O Output Unit W j I j Input Units.

elina
Télécharger la présentation

Back-propagation

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Back-propagation Chih-yun Lin 6/6/2014

  2. Agenda • Perceptron vs. back-propagation network • Network structure • Learning rule • Why a hidden layer? • An example: Jets or Sharks • Conclusions

  3. Network Structure –Perceptron O Output Unit Wj IjInput Units

  4. Network Structure –Back-propagation Network Oi Output Unit Wj,i ajHidden Units Wk,j Ik Input Units

  5. Learning Rule • Measure error • Reduce that error • By appropriately adjusting each of the weights in the network

  6. Learning Rule –Perceptron • Err = T–O • O is the predicted output • T is the correct output • WjWj+ α * Ij* Err • Ij is the activation of a unit j in the input layer • α is a constant called the learning rate

  7. Learning Rule –Back-propagation Network • Erri = Ti–Oi • Wj,iWj,i+ α * aj * Δi • Δi = Erri * g’(ini) • g’ is the derivative of the activation function g • ajis the activation of the hidden unit • Wk,jWk,j+ α * Ik * Δj • Δj = g’(inj) * ΣiWj,i* Δi

  8. Learning Rule –Back-propagation Network • E = 1/2Σi(Ti–Oi)2 • = - Ik * Δj

  9. Why a hidden layer? • (1 w1) + (1 w2) < ==> w1 + w2 < • (1 w1) + (0 w2) > ==> w1 > • (0 w1) + (1 w2) > ==> w2 > • (0 w1) + (0 w2) < ==> 0 <

  10. Why a hidden layer? (cont.) • (1 w1) + (1 w2) + (1 w3) < ==> w1 + w2 + w3 < • (1 w1) + (0 w2) + (0 w3) > ==> w1 > • (0 w1) + (1 w2) + (0 w3) > ==> w2 > • (0 w1) + (0 w2) + (0 w3) < ==> 0 <

  11. An example: Jets or Sharks

  12. Conclusion • Expressiveness: • Well-suited for continuous inputs,unlike most decision tree systems • Computational efficiency: • Time to error convergence is highly variable • Generalization: • Have reasonable success in a number of real-world problems

  13. Conclusions (cont.) • Sensitivity to noise: • Very tolerant of noise in the input data • Transparency: • Neural networks are essentially black boxes • Prior knowledge: • Hard to used one’s knowledge to “prime” a network to learn better

More Related