About this knowledge base
This post provides an overview of the content of this knowledge base.
Lecture 3: Covers language models before transformers: RNNs, Seq2Seq, LSTM models
Letcure 4: Covers transformer architecture in general and begins discussion on transformer language models
Letcure 7: Covers the basics of training and optimizing neural networks
Letcure 8: Covers Contrastive Learning: Contrastive loss functions and associated model architectures.