Deep Learning Applications by Rina Panigrahy

Deep Learning Applications by Rina Panigrahy

International Centre for Theoretical Sciences via YouTube Direct link

Softmax for multiclass output: just like max

25 of 50

25 of 50

Softmax for multiclass output: just like max

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Deep Learning Applications by Rina Panigrahy

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Statistical Physics Methods in Machine Learning
  2. 2 Deep Learning Applications
  3. 3 Tutorial: Deep Learning
  4. 4 Outline
  5. 5 Learning an unknown function
  6. 6 Learning an unknown function: like curve fitting
  7. 7 Learning a function: why?
  8. 8 Learning a function: How
  9. 9 Linear Regression: Line fitting
  10. 10 Minimize errorloss in prediction
  11. 11 Loss measures error in prediction
  12. 12 Gradient descent
  13. 13 Learning a function: Linear Regression x
  14. 14 Gradient update: BackPropagation.
  15. 15 Stochastic Gradient Descent: gradients over a few examples at a time.
  16. 16 Learning a function: Sigmoid, sign
  17. 17 Sigmoid, RELU
  18. 18 Logistic regression uses logloss
  19. 19 Deep Network. Allows rich representation Can express any function/circuit
  20. 20 Neurons
  21. 21 Network of Neurons
  22. 22 Hierarchical representation of Objects
  23. 23 Training w: SGD to Minimize loss
  24. 24 Backpropagation: Gradient Descent for one example
  25. 25 Softmax for multiclass output: just like max
  26. 26 Convergence of Gradient Descent for Model training
  27. 27 Applications
  28. 28 MNIST
  29. 29 Convolution and Pooling
  30. 30 Gradient-Based Learning Applied to Document Recognition
  31. 31 Goal
  32. 32 ImageNet
  33. 33 ILSVRC
  34. 34 Architecture
  35. 35 RELU Nonlinearity
  36. 36 96 Convolutional Kernels
  37. 37 Phone recognition on the TIMIT benchmark Mohamed, Dahl, & Hinton,
  38. 38 Word error rates from MSR, IBM, & Google Hinton et. al. IEEE signal Processing Magazine, Nov 2012
  39. 39 Speech recognition
  40. 40 RNN
  41. 41 Videos/tutorials on Deep learning applications
  42. 42 Theoretical Understanding? - Deep Learning
  43. 43 Nonconvex Optimization
  44. 44 Low rank Approximation
  45. 45 No local minima in linear networks [Kawaguchi, NIPS 16, Ge et al, ICML 17]
  46. 46 Deep Learning
  47. 47 Does well experimentally
  48. 48 With simplifications, our target functions f are...
  49. 49 Overview of Results
  50. 50 Q&A

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.