1 / 71

Matlab Sigmoid Perceptron Linear Training Small, Round Blue-Cell Tumor Classification Example

Matlab Sigmoid Perceptron Linear Training Small, Round Blue-Cell Tumor Classification Example Matlab Program for NN Analysis Algebraic Training of a Neural Network. You can use various shapes of non-linear neurons in Neural Networks. Perceptron Neural Networks.

livia
Télécharger la présentation

Matlab Sigmoid Perceptron Linear Training Small, Round Blue-Cell Tumor Classification Example

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. Matlab • Sigmoid • Perceptron • Linear • Training • Small, Round Blue-Cell Tumor Classification Example • Matlab Program for NN Analysis • Algebraic Training of a Neural Network

  2. You can use various shapes of non-linear neurons in Neural Networks

  3. Perceptron Neural Networks

  4. Biases versus Weights in Perceptrons

  5. Multi-Layer Perceptrons can classify with Boundaries and Clusters • Multi-layer perceptrons have more powerful classification capabilities • Based on number of layers and elements used we can make a classification of classifiers • We can find open and closed regions in classifications. • The next slide will show various strengths of classifiers.

  6. Sigmoid Neural Networks

  7. Smooth nonlinearity! Logsig = logistic sigmoid

  8. Sigmoid Neural Network

  9. Single Sigmoid Layer is Sufficient for any continuous function!

  10. Typical Sigmoid Neural Network Output – create your own mapping • Sigmoid gives arbitrary accuracy!

  11. Thresholded Neural Network Output • Strict YES / NO decision is sometimes useful

  12. Linear Neural Networks

  13. Training Error and Cost for a Single Linear Neuron Training error Quadratic error cost

  14. Linear Neuron Gradient Training error Quadratic error cost Single Linear Neuron

  15. Steepest-Descent Learning for a Single Linear Neuron New training parameter

  16. Backpropagation – for a Single Linear Neuron

  17. Backpropagationfor a Single Linear Neuron Training Sets

  18. Example: Microarray Training Set

  19. Steepest-Descent Algorithm for a Single-Step Perceptron

  20. Training Sigmoid Networks

  21. Training Variables for a Single Sigmoid Neuron

  22. Training a Single Sigmoid Neuron

  23. Training a Single Sigmoid Neuron Final formula for weights and biases

  24. Training a Sigmoid Network

  25. Training a Sigmoid Network

  26. Training a Sigmoid Network From previous slides

  27. Example of Classification done by a Neural Network • 62 samples from microarray • 7000 genes • 8 genes in strong feature set

  28. Small, Round Blue-Cell Tumor Classification Example

  29. Small, Round Blue-Cell Tumor Classification Example

  30. How the training set was created?

  31. Neural Network Training for the SRBCT problem • Characteristics of training method for SRBCT

  32. “Leave-One-Out” – another validation methodology

  33. “Novel-Set” Validation methodology

  34. Characteristics of methods applied

  35. Cardiac Pacemaker and EKG Signals

More Related