1 / 10

-Artificial Neural Network- Chapter 2 Basic Model

-Artificial Neural Network- Chapter 2 Basic Model. 朝陽科技大學 資訊管理系 李麗華 教授. Introduction to ANN Basic Model. Input layer Hidden layer Output layer Weights Processing Element(PE) Learning Recalling Energy function. W ij. Y 1. ‧ ‧ ‧. ‧ ‧ ‧. ‧ ‧ ‧. Y. Y j. X 1. X 2. X n.

Download Presentation

-Artificial Neural Network- Chapter 2 Basic Model

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. -Artificial Neural Network-Chapter 2 Basic Model 朝陽科技大學 資訊管理系 李麗華 教授

  2. Introduction to ANN Basic Model • Input layer • Hidden layer • Output layer • Weights • Processing Element(PE) • Learning • Recalling • Energy function

  3. Wij Y1 ‧ ‧ ‧ ‧ ‧ ‧ ‧ ‧ ‧ Y Yj X1 X2 Xn ANN Components (1/4) • Input layer:[X1,X2,…..Xn]t , where t means vector transpose. • Hidden layer: I j => net j => Y j • Output layer:Yj • Three ways of generating output: normalized, competitive output, competitive learning • Weights :Wij means the connection value between layers

  4. ANN Components (2/4) 5. Processing Element(PE) (A)Summation Function: (supervised) or (unsupervised) (B)Activity Function: or or (C)Transfer Function: • Discrete type • Linear type • Non-linear type

  5. ANN Components (3/4) 6. Learning: • Based on the ANN model used, learning is to adjust weights to accommodate a set of training pattern in the network. 7. Recalling: • Based on the ANN model used, recalling is to apply the real data pattern to the trained network so that the outputs are generated and examined.

  6. ANN Components (4/4) 8. Energy function: • Energy function is a verification function which determines if the network energy has converged to its minimum. Whenever the energy function approaches to zero, the network approaches to its optimum solution.

  7. 1 net j > 0 if netj=0 Hopfield-Tank fc. Ynj= Yn-1j 1 1 1 0 net j<0 1 net j > 0 Signum fc. if Yj = 0 0 0 -1 net j<=0 -1 -1 -1 Transfer Functions (1/3) • Discrete type transfer function: 1 net j > 0 Step function or perceptron fc. Yj= if 0 net j <=0

  8. 1 net j > 0 Yj = if Signum0 fc. 0 netj = 0 -1 net j<0 1 1 1 net j > 0 Ynj = net j = 0 if Yn-1j -1 net j<0 0 0 -1 -1 Transfer Functions (2/3) • Discretetype transfer function: BAM fc.

  9. Transfer Functions (3/3) • Linear type: • Nonlinear type transfer function: Yj = net j net j net j > 0 Yj = if 0 net j <=0 Yj = Sigmoid function Yj = Hyperbolic Tangent function

  10. E = where E is the energy value ΔW= this is the value for adjusting weight Wij E = Energy function (a) The energy function for supervised network learning: (b) The energy function for unsupervised network learning: ΔW= this is the value for adjusting weight Wij

More Related