2. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Day 2 Afternoon: Hands-on
• 2:15pm - Your Hands-on lab : Each team choose one of the 3 labs
• (Each team: 2 members team / pair up )
• 3:00pm – Hack-a-thon AI for GOOD CAUSE : Code your idea
• ( Each team: 1 faculty + few student )
3. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Choose your hands-on lab
Deep Learning
1. Rock paper game - Image
classification MEDIUM EASY
2. Image Segmentation
HARDER
Output of AI: Scalar values
(numbers)
Generative
Deep Learning
3. Auto encoder MEDIUM
4. GAN HARDER
Output of AI: Vectors , Images
AI that creates
another AI
5. NAS HARDER (with 1 bug)
Output of AI: Neural networks
For hands-on lab , visit the github
https://github.com/rajagopalmotivate1/DeepLearningLab
4. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Code #1 : Rock paper scissor game
•
5. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Code #2: Segmentation
6. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Code #3: Auto correct a selfie
•
7. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Code #4: Creativity / GAN : Generate an
picture
•
8. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Code #5: neural architecture search
•
9. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Hack-a-thon AI for GOOD CAUSE :
Code your idea
( Each team: 1 faculty + few student
• Find a problem you want to solve
• Code the solution
10. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Quiz #1
Is it possible to map hand signs for deaf speech
Hand signs Speech
11. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Voice for the dumb
12. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
• Indian Sign lang
13. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Rock paper scissor game
•
14. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
2 min fun game :
Play with AI
15. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
16. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
17. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
18. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
19. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
20. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
21. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
• Layer to be used as an entry point into a Network (a graph of layers).
•
22. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
23. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
24. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
25. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
26. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
27. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
28. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
29. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
• Batch size x epochs = total no of images
30. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
31. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Binary
Multi class classification
32. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
33. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
A neural network is parameterized by its
weights
34. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
A loss function measures the quality of the
network’s output
The loss function takes the predictions
of the network and the true target.
and computes a distance score,
capturing how well the network has
done on this specific example
Credits, Deep Learning with Python
35. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
The loss score is used as a feedback signal to
adjust the weights
36. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Method: 7 steps to develop your Deep Learning model
1: Define problem
Collect data representing
the purpose
2: Format the data
Spilt data, vectorize, reshape,
normalize, OHE
3: Design the network Design the Neural Network
4: Define loss Think of what to optimize for
5: Train the network
Allow the network to learn
patterns in the data
6: Validate & Improve Power of generalization?
7: Predict Predict
Adjust model’s
capacity to learn
“just the patterns”
Develop model
that overfits
Develop 1st model
37. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
38. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
How to learn to code Deep Leaning?
Learn in 3 months from
https://www.deeplearning.ai/tensorflow-in-practice/