Deep Learning (Video Book by Me)

This site is dedicated to the simplest video tutorials on Deep Learning. My aim is to prepare a free & interactive video book on Deep Learning. I have used my knowledge and experience to prepare these tutorials. All feedback and suggestions are welcome (email me at nirajrkumar@gmail.com or nirajrkumar@yahoo.com).

As, scientific development is an endless process, so I will keep updating it. Clicking on the link will drive you to the YouTube page for related content. Or You can use the link: https://www.youtube.com/channel/UC95bRAbJdLyXGbMfNemr9lQ

Deep Learning

1. Bias Variance Tradeoff

Bias Variance Tradeoff

2. Deep Learning Basics (Gradient Descent)

Gradient Descent & Batch Gradient Descent Made Easy

Stochastic Gradient Descent & Mini Batch Gradient Descent Made Easy

3. Deep Learning Basics (Vanishing and Exploding Gradient Problems)

Vanishing and Exploding Gradient Problems Part-1
Vanishing and Exploding Gradient Problems Part-2

4. Deep Learning Basics (Optimizers)

Momentum and RMSProp Made Easy

ADAM(Adaptive Moment Estimation)

5. Deep Learning Cost Functions

Entropy and Cross-Entropy

Binary Cross Entropy Loss

Categorical Cross Entropy Loss

6. Regularization in Deep Learning

L2 Regularization in Deep Learning and Weight Decay: This tutorial discusses the L2 Regularization with Deep Learning. It also explains, “how L2 regularization results in weight decay in Deep Networks?”.

L1 Regularization in Deep Learning and Sparsity: This tutorial discusses the L1-Regularization with Deep learning and also explains how L1 regularization results in the sparsity.

7. Saddle Points Problem in Deep Learning

Saddle Points Problem in Deep Learning

8. CNN (Convolutional Neural Networks)

1. Basics of CNN, 2. Convolution Operation., 3. Pooling Operation., 4. Calculating I/O size,

1. Basic of Padding in Convolutional Neural Network, 2. The Padding I/O Size Computation., 3. Some Insight about Padding

1.Basics of Stride in Convolutional Neural Network, 2. Convolution and Pooling Operation with Higher Stride Values., 3. Some Insight about Strides

9. Deep Learning using Deep Neural Network

Deep Learning using Deep Neural Network Part-1
Deep Learning using Deep Neural Network Part-2
Deep Learning using Deep Neural Network Part-2

10. Word2Vec Systems (CBOW)

Word2vec: Continuous bag-of-words architecture Part-1

Word2vec: Continuous bag-of-words architecture Part-2

11. Word2Vec Systems (SKIP GRAM)

Word2Vec-Skip-Gram Part-1

Word2Vec-Skip-Gram Part-2

12. Deep Learning using Recurrent Neural Network

Recurrent Neural Network Part-1

Recurrent Neural Network Part-2

13. LSTM (Long Short Term Memory)

LSTM (Long Short Term Memory) Network Part-1

LSTM (Long Short Term Memory) Network Part-2

LSTM (Long Short Term Memory) Network Part-3

14. Language Model and Deep Learning

Language Model and Deep Learning Part-1

Language Model and Deep Learning Part-2

Language Model and Deep Learning Part-3

15. Attention-Based Models

Attention in Deep Learning (Simplified)

Self Attention Made Easy

Hierarchical Attention Networks Simplified

16. Transformer Model in NLP

Transformer Model Part-1

Transformer Model Part-2

17. BERT Models for NLP

BERT PART 1 (Bidirectional Encoder Representations from Transformers); Contains. 1. Important Points Related to BERT; 2. BERT Embedding Layer Architecture

BERT – Part-2 (Bidirectional Encoder Representations from Transformers); Contains (Detailed Architecture). – 1. Bi-directional Transformers inside BERT; 2. Bidirectional Self-Attention; 3. Multi-Headed Attention

(Detailed Architecture).; 1. Role of Layer Normalization in BERT, 2. Role of Residual Connections in BERT, 3. Overall Functioning

18. XLNet Models for NLP

XLNet Made Easy Part-1 (Contains. 1. BERT Vs XLNet, 2. Overview of XLNet, 3. Autoregressive Language Modeling)

XLNet Made Easy PART 2 (Contains. 1. Permutation Language Modeling for XLNet, 2. Merits and Demerits of Permutation Language Modeling.)

XLNet Made Easy PART 3 (Contains. 1. Masked Attention for XLNet, 2. Two Stream Self Attention for XLNet, 3. Final Working Overview of XLNet)

19. Transfer Learning

Transfer Learning Part-1 (Overview of Transfer Learning)

Transfer Learning Part-2 (Multi-Task Learning)

To be Added

Transfer Learning Part-3

20. Restricted Boltzmann Machine

Restricted Boltzmann Machine Part-1

Restricted Boltzmann Machine Part-2

Restricted Boltzmann Machine Part-3

21. Deep Learning using Deep Belief Network

Deep Learning using Deep Belief Network Part-1

Deep Learning using Deep Belief Network Part-2

22. Logistic Regression

Logistic Regression

23. Graph Neural Networks

Graph Neural Network Part-1

Graph Neural Network Part-2

24. Transformer to Transformer-RNN/T2RNN

Transformer-RNN/T2RNN Part-1

Transformer-RNN/ T2RNN Part-2

25. Scalability of the Transformer Architecture

Deep-Learning: How to improve the Scalability of The Transformer Architecture Part-1