a language model that create names. inspired by Andrej Karpathy
The model get enhanced as per the following implimentations
- Biagram - basic probability based model
- implemented in the [Language_Models]_makemore.ipynb
- MLP: A Neural Probabilistic Language Model
- implemented in the [Language_Models]_makemore_MLP.ipynb
- "Kaiming init" paper: https://arxiv.org/abs/1502.01852
- BatchNorm paper: https://arxiv.org/abs/1502.03167
- Good paper illustrating some of the problems with batchnorm in practice: https://arxiv.org/abs/2105.07576
- CN: Paper by deepmind
- In progress
- RNN: Recurrent neural network based language model
- In progress
- LSTM: Generating Sequences With Recurrent Neural Networks
- In progress
- GRU: On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- In progress
- Transformer Attention Is All You Need
- In progress