Learning track
From Text to Tensors
See how text becomes tokens, vectors, and numerical structures a neural network can process.
foundations · 7 available lessons
From Text to Tensors
See how text becomes tokens, vectors, and numerical structures a neural network can process.
- Why computers can't read
- Tokenization I: characters, words, and subwords
- Tokenization II: BPE, step by step
- Tokenization III: SentencePiece, byte-level, and why token counts bite
- Embeddings: meaning as geometry
- word2vec, GloVe, and the analogy trick
- Entropy, perplexity, and what 'good' means