Deep Learning(CS7015): Lec 9.4 Better initialization strategies

preview_player
Показать описание
lec09mod04
  1. NPTEL-NOC IITM
  2. deep learning
  3. prof.mitesh khapra
  4. iitmadras
  5. nptel deep learning
Рекомендации по теме
Deep Learning(CS7015): Lec 0:06:21

Deep Learning(CS7015): Lec 9.1 A quick recap of training deep neural networks

Deep Learning(CS7015): Lec 0:04:46

Deep Learning(CS7015): Lec 1.9 (Need for) Sanity

Deep Learning(CS7015): Lec 0:40:48

Deep Learning(CS7015): Lec 5.9 Gradient Descent with Adaptive Learning Rate

Deep Learning(CS7015): Lec 0:15:44

Deep Learning(CS7015): Lec 9.5 Batch Normalization

Deep Learning(CS7015): Lec 0:18:45

Deep Learning(CS7015): Lec 5.4 Momentum based Gradient Descent

Deep Learning(CS7015): Lec 0:08:48

Deep Learning(CS7015): Lec 8.3 True error and Model complexity

Deep Learning(CS7015): Lec 0:26:50

Deep Learning(CS7015): Lec 4.3 Output functions and Loss functions

Deep Learning(CS7015): Lec 0:16:58

Deep Learning(CS7015): Lec 11.3 Convolutional Neural Networks

Deep Learning(CS7015): Lec 0:26:18

Deep Learning(CS7015): Lec 7.4 Denoising Autoencoders

Deep Learning(CS7015): Lec 0:13:52

Deep Learning(CS7015): Lec 4.4 Backpropagation (Intuition)

Deep Learning(CS7015): Lec 0:24:57

Deep Learning(CS7015): Lec 9.2 Unsupervised pre-training

Deep Learning(CS7015): Lec 0:08:44

Deep Learning(CS7015): Lec 13.1 Sequence Learning Problems

Deep Learning(CS7015): Lec 0:20:49

Deep Learning(CS7015): Lec 11.4 CNNs (success stories on ImageNet)

Deep Learning(CS7015): Lec 0:31:20

Deep Learning(CS7015): Lec 14.2 Long Short Term Memory(LSTM) and Gated Recurrent Units(GRUs)

Deep Learning(CS7015): Lec 0:27:38

Deep Learning(CS7015): Lec 15.3 Attention Mechanism

Deep Learning(CS7015): Lec 0:09:26

Deep Learning(CS7015): Lec 10.1 One-hot representations of words

Deep Learning(CS7015): Lec 0:18:29

Deep Learning(CS7015): Lec 11.1 The convolution operation

Deep Learning(CS7015): Lec 0:09:11

Deep Learning(CS7015): Lec 5.1 & Lec 5.2 Recap: Learning Parameters: Guess Work, Gradient Descen...

Deep Learning(CS7015): Lec 0:14:41

Deep Learning(CS7015): Lec 10.3 SVD for learning word representations

Deep Learning(CS7015): Lec 0:14:24

Deep Learning(CS7015): Lec 13.3 Backpropagation through time

Deep Learning(CS7015): Lec 0:21:55

Deep Learning(CS7015): Lec 15.1 Introduction to Encoder Decoder Models

Deep Learning(CS7015): Lec 0:16:37

Deep Learning(CS7015): Lec 8.11 Dropout

Deep Learning Part 0:47:55

Deep Learning Part - II (CS7015): Lec 19.3 Setting up a Markov Chain for RBMs

What is Dropout 0:00:26

What is Dropout for Neural Networks (Deep Learning) #shorts

Комментарии
Автор

15:24 Variance of a sum is the sum of variances only if all the covariances are 0, one such case being when all the random variables are independent.

mainakghosh
Автор

Why did sir not consider activation function after first layer in the proof? After calculating S11 there will also be non linearity g(S11) which will be input to second layer and not directly S11. We are proving so that activation has variance and ignoring the activation in proof is just too superficial.

rajatkumarsingh
Автор

I still did not get why we are interested in variance at each neuron.

luckysunda
Автор

How can we calculate the expectation of constant W₁ᵢ because if we put i=1 to n then it becomes constant. The expectation of constant is contant itself.

suhaneshivam
Автор

Why gradient for tanh or sigmoid at x=0 is equal to 0. The value of gradient at x=0 for sigmoid is 0.25

binod