
Lecture 40 of 61 · Deep Learning
P. K. Biswas
Deep Learning · 61 lectures
61 lectures
Lecture 1
1: Introduction
2: Feature Descriptor - I
3: Feature Descriptor - II
4: Bayesian Learning - I
5: Bayesian Learning - II
6: Discriminant Function - I
7: Discriminant Function - II
8: Discriminant Function - III
9: Linear Classifier
10: Linear Classifier - II
11: Support Vector Machine - I
12: Support Vector Machine - II
13: Linear Machine
14: Multiclass Support Vector Machine - I
15: Multiclass Support Vector Machine -II
16: Optimization
17: Optimization Techniques in Machine Learning
18: Nonlinear Functions
19: Introduction to Neural Network
20: Neural Network -II
21: Multilayer Perceptron
22: Multilayer Perceptron - II
23: Backpropagation Learning
24: Loss Function
25: Backpropagation Learning - Example
26: Backpropagation Learning- Example II
27: Backpropagation Learning- Example III
28: Autoencoder
29: Autoencoder Vs. PCA I
30: Autoencoder Vs. PCA II
31: Autoencoder Training
32: Autoencoder Variants I
33: Autoencoder Variants II
34: Convolution
35: Cross Correlation
36: CNN Architecture
37: MLP versus CNN, Popular CNN Architecture: LeNet
38: Popular CNN Architecture: AlexNet
39: Popular CNN Architecture: VGG16, Transfer Learning
40: Vanishing and Exploding Gradient
41: GoogleNet
42: ResNet, Optimisers: Momentum Optimiser
43: Optimisers: Momentum and Nesterov Accelerated Gradient
44: Optimisers: Adagrad Optimiser
45: Optimisers: RMSProp, AdaDelta and Adam Optimiser
46: Normalization
47: Batch Normalization-I
48: Batch Normalization-II
49: Layer, Instance, Group Normalization
50: Training Trick, Regularization,Early Stopping
51: Face Recognition
52: Deconvolution Layer
53: Semantic Segmentation - I
54: Semantic Segmentation - II
55: Semantic Segmentation - III
56: Image Denoising
57: Variational Autoencoder
58: Variational Autoencoder - II
59: Variational Autoencoder - III
60: Generative Adversarial Network