Deep Learning topic cover in this repository

ANN

1. Introduction
2. Perceptron
3. Forward Propagation.
4. Loss Functions
5. Back Propagation.
6. Memoization
7. GD in neural network
8. Improve neural network performance (ⅰ) Dropout Layer (ii) Regularization. (iii) Activation Functions (iv) Weight Initialization (v) Batch Normalization (vi) Optimizers

CNN

1. CNN Introduction
2. Padding and Strides
3. Pooling Layer
4. Back propagation in CNN
5. Pre-trained models
6. Transfer Learning

RNN

1. RNN Introduction
2. Forward Propagation
3. Types of RNN
4. Backward Propagation
5. Problems with RNN
6. LSTM Introduction
7. LSTM Architecture.
8. GRU
9. Deep RNN

Seq2Seq Models

1. Encoder-Decoder
2. Attention Mechanism
3. Transformers Introduction
4. Self Attention
5. Bahdanau and Luong Attention.
6. Multi-Head Attention
7. positional Encoding.
8. Layer Normalization
9. Masked Multi-Head Attention
10. Cross Attention
11. Transformer's encoder Architecture.
12. Transformen's Decoder Architecture.