Learning track
From Text to Tensors
See how text becomes tokens, vectors, and numerical structures a neural network can process.
From Text to Tensors
See how text becomes tokens, vectors, and numerical structures a neural network can process.
- 02.01Why computers can't read→
- 02.02Tokenization I: characters, words, and subwords→
- 02.03Tokenization II: BPE, step by step→
- 02.04Tokenization III: SentencePiece, byte-level, and why token counts bite→
- 02.05Embeddings: meaning as geometry→
- 02.06word2vec, GloVe, and the analogy trick→
- 02.07Entropy, perplexity, and what 'good' means→