deep-learning
The recurrent hidden state
taught
Taught in
-
From shared weights to a hidden state
Deep Learning / Neural Networks
-
Unrolling a recurrent network
Deep Learning / Neural Networks
-
A character-level language model
Deep Learning / Neural Networks
-
What recurrent networks struggle with
Deep Learning / Neural Networks
-
Sequence applications: two architectures, one task
Deep Learning / Neural Networks
-
From recurrence to attention
Wiring Language Models
Requires
- sequence-modeling required
Required by
- Backpropagation through time required
- Deep and bidirectional recurrent networks required
- LSTM gating required
- The encoder-decoder architecture required
Local knowledge map
Local knowledge map
Click to expand
Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.