IIT Kharagpur · Engineering

Deep Learning For Visual Computing

Prof. Debdoot Sheet · 61 free video lectures

61 video lectures. Topics: Introduction to Visual Computing; Feature Extraction for Visual Computing; Feature Extraction with Python; Neural Networks for Visual Computing; Classification with Perceptron Model; Introduction to Deep Learning with Neural Networks; Multilayer Perceptron and Deep Neural…

▶ Play on Open Lecture HallCourse page ↗

Lectures

  1. Lecture 1 : Introduction to Visual Computing
  2. Lecture 2 : Feature Extraction for Visual Computing
  3. Lecture 3: Feature Extraction with Python
  4. Lecture 4: Neural Networks for Visual Computing
  5. Lecture 5: Classification with Perceptron Model
  6. Lecture 6 : Introduction to Deep Learning with Neural Networks
  7. Lecture 7 : Introduction to Deep Learning with Neural Networks
  8. Lecture 8 : Multilayer Perceptron and Deep Neural Networks
  9. Lecture 9 : Multilayer Perceptron and Deep Neural Networks
  10. Lecture 10 : Classification with Multilayer Perceptron
  11. Lecture 11 : Autoencoder for Representation Learning and MLP Initialization
  12. Lecture 12 : MNIST handwritten digits classification using autoencoders
  13. Lecture 13 ; Fashion MNIST classification using autoencoders
  14. Lecture 14 : ALL-IDB Classification using autoencoders
  15. Lecture 15 : Retinal Vessel Detection using autoencoders
  16. Lecture 16 : Stacked Autoencoders
  17. Lecture 17 : MNIST and Fashion MNIST with Stacked Autoencoders
  18. Lecture 18 : Denoising and Sparse Autoencoders
  19. Lecture 19 : Sparse Autoencoders for MNIST classification
  20. Lecture 20 : Denoising Autoencoders for MNIST classification
  21. Lecture 21 : Cost Function
  22. Lecture 22 : Classification cost functions
  23. Lecture 23 : Optimization Techniques and Learning Rules
  24. Lecture 24 : Gradient Descent Learning Rule
  25. Lecture 25 : SGD and ADAM Learning Rules
  26. Lecture 26 : Convolutional Neural Network Building Blocks
  27. Lecture 27 : Simple CNN Model: LeNet
  28. Lecture 28 : LeNet Definition
  29. Lecture 29 : Training a LeNet for MNIST Classification
  30. Lecture 30 : Modifying a LeNet for CIFAR
  31. Lecture 31 : Convolutional Autoencoder and Deep CNN
  32. Lecture 32 : Convolutional Autoencoder for Representation Learning
  33. Lecture 33 : AlexNet
  34. Lecture 34 : VGGNet
  35. Lecture 35 : Revisiting AlexNet and VGGNet for Computational Complexity
  36. Lecture 36: GoogLeNet - Going very deep with convolutions
  37. Lecture 37 : GoogLeNet
  38. Lecture 38: ResNet - Residual Connections within Very Deep Networks and DenseNet - Densely connected networks
  39. Lecture 39: ResNet
  40. Lecture 40: : DenseNet
  41. Lecture 41 : Space and Computational Complexity in DNN
  42. Lecture 42 : Assessing the space and computational complexity of very deep CNNs
  43. Lecture 43: Domain Adaptation and Transfer Learning in Deep Neural Networks
  44. Lecture 44 : Transfer Learning a GoogLeNet
  45. Lecture 45 : Transfer Learning a ResNet
  46. Lecture 46 Activation pooling for object localization
  47. Lecture 47: Region Proposal Networks (rCNN and Faster rCNN)
  48. Lecture 48:GAP + rCNN
  49. Lecture 49: Semantic Segmentation with CNN
  50. Lecture 50: UNet and SegNet for Semantic Segmentation
  51. Lecture 51 : Autoencoders and Latent Spaces
  52. Lecture 52 : Principle of Generative Modeling
  53. Lecture 53 : Adversarial Autoencoders
  54. Lecture 54 : Adversarial Autoencoder for Synthetic Sample Generation
  55. Lecture 55: Adversarial Autoencoder for Classification
  56. Lecture 56 : Understanding Video Analysis
  57. Lecture 57 : Recurrent Neural Networks and Long Short-Term Memory
  58. Lecture 58 : Spatio-Temporal Deep Learning for Video Analysis
  59. Lecture 59 : Activity recognition using 3D-CNN
  60. Lecture 60 : Activity recognition using CNN-LSTM
  61. Live Session 04-11-2020

From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IIT Kharagpur.

Open Lecture Hall is free, with no ads and no sign-up. It is not run by or connected to any university; the lectures are the universities' own free recordings, played from where they host them. About & rights