Vanishing and Exploding Gradients + Beam Search: How Early Neural Networks Learned and Generated Text Before Transformers

LSTM and GRU Explained: How Neural Networks Learned to Remember Before Transformers

Basic RNNs and Bidirectional RNNs Explained: How Neural Networks Learned to Process Sequences Before Transformers

GloVe and Bias in Embeddings: How Meaning and Prejudice Emerge from Language Statistics