![Cross Validation
describe Network do
%w[English Finnish German Norwegian Polish Swedish].each do |lang|
it "Trains and cross-validates with an error of 5% for #{lang}"
end
end](https://image.slidesharecdn.com/neuralnetsinmiami-131109135803-phpapp01/85/Rubyconf-Neural-Networks-33-320.jpg)
Rubyconf Neural Networks
- 1. Test Driven Neural Networks Matthew Kirk - Modulus 7
- 6. Ruby has tools too
- 8. Ruby is not Complex Math
- 9. Today we’ll cover • • • • What feed forward neural networks are How to classify strings to languages using Neural Nets How to do it in a TDD fashion Demonstration
- 10. Neural Networks! aka the sledge hammer of functional relationships
- 11. Neural Networks
- 12. Input layer
- 13. Hidden layer
- 14. How many Neurons? • 2/3 * Input layer count + output count is a good start • Aggregation over expansion so less neurons in the hidden layer than on the input layer.
- 15. Output layer
- 16. Neurons
- 17. Digital Logic
- 18. Fuzzy Logic
- 19. Activation Functions • Sigmoid • Elliott • Gaussian • Linear • Threshold • Cosine and Sine
- 20. Activation Functions • Sigmoid => Learning Curve • Elliott => Learning Curve • Gaussian => Bell curve • Linear => Line • Threshold => Yes or No • Cosine and Sine => Periodic
- 22. Training Algorithms • Quickprop • RProp => Use this • Back propagation
- 23. Visually What they do
- 24. Just the tip of the Neural Nets iceberg
- 26. Specifically • English • German • Polish • Swedish • Finnish • Norwegian
- 27. Data Collection • Using the most translated book in the world “The Bible” to collect sentences used in each of these languages.
- 28. Now What?
- 31. TDD Neural Nets
- 32. Test the Seams describe Language do it 'has the proper keys for each vector' it 'sums to 1 for all vectors' it 'returns characters that is a unique set of characters used' end
- 33. Cross Validation describe Network do %w[English Finnish German Norwegian Polish Swedish].each do |lang| it "Trains and cross-validates with an error of 5% for #{lang}" end end
- 34. Ockham’s Razor
- 35. Demo
- 37. Conclusion This is just the beginning Go learn more become more adept at data analysis