1 / 10

Lecture 9 MLP (I): Feed-forward Model

Lecture 9 MLP (I): Feed-forward Model. Outline. Multi-Layer Perceptron Structure Feed Forward Model XOR Example MLP Applications. Multi-Layer Perceptron Structure. A Three Layer Feed-forward Multi-Layer Perceptron. Two Layer Perceptron XOR Gate. Decision Boundaries of XOR.

jaafar
Download Presentation

Lecture 9 MLP (I): Feed-forward 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. Lecture 9 MLP (I): Feed-forward Model

  2. Outline • Multi-Layer Perceptron Structure • Feed Forward Model • XOR Example • MLP Applications (C) 2001-2003 by Yu Hen Hu

  3. Multi-Layer Perceptron Structure A Three Layer Feed-forward Multi-Layer Perceptron (C) 2001-2003 by Yu Hen Hu

  4. Two Layer Perceptron XOR Gate (C) 2001-2003 by Yu Hen Hu

  5. Decision Boundaries of XOR • Linear Hyper-planes as decision boundaries x1 – x2 – 0.5 = 0; and x2 – x1 – 0.5 = 0 (C) 2001-2003 by Yu Hen Hu

  6. 1 1 2.5 1 1 5 5 3 x 2 z 1 5 y 4 1 5 1 MLP Nonlinear Mapping (C) 2001-2003 by Yu Hen Hu

  7. MLP Feed-forward model Notation • (k) – Index of individual feature vectors, 1 k K. • () --Layer index, superscript, 0  L. = 0 input layer,  = L  output layer • i, j – ith and jth neuron in each layer, subscript Example: • zi()(k): the output of ith neuron in the th layer corresponding to the kth feature vector. • wij(): the value of the synaptic weight that connect the output of the jth neuron at 1th layer to the jth neuron at the th layer. The value of the weight is updated once every epoch. (C) 2001-2003 by Yu Hen Hu

  8. MLP Feed-forward model • Note that , and • The input layer usually consists of linear elements. Thus, a 2-layer MLP will have two layers of non-linear neurons: the hidden layer, and the output layer. (C) 2001-2003 by Yu Hen Hu

  9. Applications to Classification • Classification: Match output class to target class. MLP assigns each input feature vector to a membership of a particular class i. (C) 2001-2003 by Yu Hen Hu

  10. Applications to Approximation • Approximation (regression, modeling) : Targets are real numbers instead of binary class membership. (C) 2001-2003 by Yu Hen Hu

More Related