AI Basics and Neural Networks Introduction

Transcript

1. Artificial Intelligence Basics and Neural Networks Introduction Frederico Jordan
2. What is Artificial Intelligence (AI)?
3. AI in Popular Culture
4. AI Effect "AI is whatever hasn't been done yet." Douglas Hofstadter "Every time we figure out a piece of it, it stops being magical; we say, 'Oh, that's just a computation.'" Rodney Brooks
5. Types of Artificial Intelligence
6. Weak AI (Narrow AI) Non-sentient machine intelligence, typically focused on a narrow task.
7. Strong AI Hypothetical Sentient machine (with consciousness, sentience and mind).
8. Strong AI Hypothetical Sentient machine (with consciousness, sentience and mind). Artificial general intelligence (AGI): Machine with the ability to apply intelligence to any problem, rather than just one specific problem "At least as smart as a typical human".
9. Superintelligence Hypothetical Artificial intelligence far surpassing that of the brightest and most gifted human minds.
10. Artificial Intelligence Branches • Machine learning ◦ Neural networks ▪ Perceptron ▪ Recurrent neural network ▪ Convoluted neural network ◦ Support Vector Machines (SVM) • Fuzzy systems • Evolutionary algorithms ◦ Genetic algorithm ◦ Differential evolution • Swarm Intelligence • Probabilistic methods
11. Neural Networks What is this ?
12. Neural Networks Uses
13. OK, but what are they?
14. Let’s get TECHNICAL!
15. Perceptrons
16. Perceptrons • (-2) and (-2) – Weights (W) • 3 – Bias/Threshold (b)
17. Perceptrons
18. Perceptrons • x 1 – Is it raining? • x 2 – Does your girlfriend/boyfriend want to go? • x 3 – Is it near public transportation?
19. Perceptrons
20. Neural Networks Finally!
21. Perceptrons
22. Neural Networks
23. How do they learn?
24. Real World Problem!
25. Recognizing Handwritten Digits
26. Database The MNIST (Modified National Institute of Standards and Technology) database Contains 60,000 training images and 10,000 testing images.
27. Neural Network Architecture
28. Measuring Outcome! Cost Function
29. Neural Network Architecture
30. Neural Network Architecture
31. Cost Function
32. Neural Networks
33. Learning
34. Gradient Descent
35. Cost Function
36. Gradient Descent
37. Gradient Descent
38. Bonus github.com/fredericojordan/neural playground.tensorflow.org
39. Acknowledgements NeuralNetworksAndDeepLearning.com Michael Nielsen
40. Thank you!