Embedding layers in neural networks

Git workflow extras (including merge conflicts)

A Git workflow

Evaluating word embeddings (NLP817 7.12)

GloVe word embeddings (NLP817 7.11)

Skip-gram with negative sampling (NLP817 7.10)

Continuous bag-of-words (CBOW) (NLP817 7.9)

Skip-gram example (NLP817 7.8)

Skip-gram as a neural network (NLP817 7.7)

Skip-gram optimisation (NLP817 7.6)

Skip-gram model structure (NLP817 7.5)

Skip-gram loss function (NLP817 7.4)

Skip-gram introduction (NLP817 7.3)

One-hot word embeddings (NLP817 7.2)

Why word embeddings? (NLP817 7.1)

What can large spoken language models tell us about speech? (IndabaX South Africa 2023)

Hidden Markov models in practice (NLP817 5.13)

The log-sum-exp trick (NLP817 5.12)

Why expectation maximisation works (NLP817 5.11)

Soft expectation maximisation for HMMs (NLP817 5.10)

Hard expectation maximisation for HMMs (NLP817 5.9)

Learning in HMMs (NLP817 5.8)

The forward algorithm for HMMs (NLP817 5.7)

Why do we want the marginal probability in an HMM? (NLP817 5.6)

Viterbi HMM example (NLP817 5.5)

The Viterbi algorithm for HMMs (NLP817 5.4)

The three HMM problems (NLP817 5.3)

Hidden Markov model definition (NLP817 5.2)

A first hidden Markov model example (NLP817 5.1)

What are perplexity and entropy? (NLP817 4)