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.

Solving Simple Problems With Neural Networks presented by Mark Nguyen.


Published on

The Kansas City Machine Learning Group hosted a presentation by Mark Nguyen on the use of Machine Learning and Neural Networks for image recognition and fingerprint detection. An attachment of his presentation is below.

Published in: Education
  • Be the first to comment

  • Be the first to like this

Solving Simple Problems With Neural Networks presented by Mark Nguyen.

  1. 1. Solving simple problems using Neural Network Mark Nguyen
  2. 2. Neural Network
  3. 3. Contents I. Face recognition using single layer neural network 1. Database 2. Source code 3. Result II. Face recognition using deep neural network III. Spoof fingerprint detection using convolution neural network
  4. 4. Face Recognition using single layer NN • ten different images of each of 40 distinct subjects • the images were taken at different times, varying the lighting, facial expressions and facial details • the size of each image is 92x112 pixels, with 256 grey levels per pixel
  5. 5. Examples
  6. 6. Source Code
  7. 7. results
  8. 8. Face Recognition using deep NN
  9. 9. Face Recognition using deep NN • First 6 images of each subject are used to train the network • Multiclass classification
  10. 10. Source code
  11. 11. Autoencoders
  12. 12. Multiclass classification results
  13. 13. Machine learning
  14. 14. Machine learningFeature presentation
  15. 15. Convolution
  16. 16. Alexnet “We trained a large, deep convolutional neural network to classify the 1.2 million high- resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes”
  17. 17. Spoof fingerprint detection using Convolutional Neural Network
  18. 18. Dataset • 4 Different fingerprint sensors • 5 different spoof fingerprint materials
  19. 19. Source code
  20. 20. Result
  21. 21. Thank you