1 / 11

Artificial Neural Networks

Artificial Neural Networks. Torsten Reil torsten.reil@zoo.ox.ac.uk. Example: Voice Recognition. Task: Learn to discriminate between two different voices saying “Hello” Data Sources Steve Simpson David Raubenheimer Format Frequency distribution (60 bins) Analogy: cochlea.

rianne
Download Presentation

Artificial Neural Networks

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 Networks Torsten Reil torsten.reil@zoo.ox.ac.uk

  2. Example: Voice Recognition • Task: Learn to discriminate between two different voices saying “Hello” • Data • Sources • Steve Simpson • David Raubenheimer • Format • Frequency distribution (60 bins) • Analogy: cochlea

  3. Network architecture • Feed forward network • 60 input (one for each frequency bin) • 6 hidden • 2 output (0-1 for “Steve”, 1-0 for “David”)

  4. Steve • Presenting the data David

  5. Steve 0.43 • Presenting the data (untrained network) 0.26 David 0.73 0.55

  6. Steve 0.43 – 0 = 0.43 • Calculate error 0.26 –1 = 0.74 David 0.73 – 1 = 0.27 0.55 – 0 = 0.55

  7. Steve 0.43 – 0 = 0.43 • Backprop error and adjust weights 0.26 – 1 = 0.74 1.17 David 0.73 – 1 = 0.27 0.55 – 0 = 0.55 0.82

  8. Repeat process (sweep) for all training pairs • Present data • Calculate error • Backpropagate error • Adjust weights • Repeat process multiple times

  9. Steve 0.01 • Presenting the data (trained network) 0.99 David 0.99 0.01

  10. Results – Voice Recognition • Performance of trained network • Discrimination accuracy between known “Hello”s • 100% • Discrimination accuracy between new “Hello”’s • 100% • Demo

  11. Results – Voice Recognition (ctnd.) • Network has learnt to generalise from original data • Networks with different weight settings can have same functionality • Trained networks ‘concentrate’ on lower frequencies • Network is robust against non-functioning nodes

More Related