Recurrent neural networks#
In this session we learn about language modeling. We look at a general definition of a language model and then zoom in on left-to-right LMs, for which discuss training, prediction and evaluation. We study recurrent neural networks as a first instance of neural language models.
Learning goals for this session#
become familiar with language modeling
causal (left-to-right) models
training, prediction, evaluation
meet a first neural LM: recurrent neural networks
implement a character-level RNN
loss from next-word surprisal
teaching forcing
autoregressive (greedy) decoding
Slides#
Here are the slides for this session.
Practical exercises#
There is one notebook with hands-on exercises for RNNs.