andy
5a592c8c7c
Affected files: .obsidian/graph.json .obsidian/workspace-mobile.json .obsidian/workspace.json STEM/AI/Ethics.md STEM/AI/Neural Networks/Activation Functions.md STEM/AI/Neural Networks/CNN/CNN.md STEM/AI/Neural Networks/Deep Learning.md STEM/AI/Neural Networks/MLP/Back-Propagation.md STEM/AI/Neural Networks/MLP/MLP.md STEM/AI/Neural Networks/Neural Networks.md STEM/AI/Neural Networks/Properties+Capabilities.md STEM/AI/Neural Networks/RNN/LSTM.md STEM/AI/Neural Networks/RNN/RNN.md STEM/AI/Neural Networks/RNN/VQA.md STEM/AI/Neural Networks/SLP/SLP.md STEM/AI/Neural Networks/Training.md STEM/AI/Neural Networks/Transformers/Attention.md STEM/AI/Neural Networks/Transformers/LLM.md STEM/AI/Neural Networks/Transformers/Transformers.md STEM/Signal Proc/System Classes.md STEM/img/back-prop-equations.png STEM/img/back-prop-weight-changes.png STEM/img/back-prop1.png STEM/img/back-prop2.png STEM/img/cnn+lstm.png STEM/img/deep-digit-classification.png STEM/img/deep-loss-function.png STEM/img/llm-family-tree.png STEM/img/lstm-slp.png STEM/img/lstm.png STEM/img/matrix-dot-product.png STEM/img/ml-dl.png STEM/img/photo-tensor.png STEM/img/relu.png STEM/img/rnn-input.png STEM/img/rnn-recurrence.png STEM/img/slp-arch.png STEM/img/threshold-activation.png STEM/img/transformer-arch.png STEM/img/vqa-block.png
17 lines
543 B
Markdown
17 lines
543 B
Markdown
Recurrent Neural Network
|
|
|
|
- Hard to train on long sequences
|
|
- Weights hold memory
|
|
- Implicit
|
|
- Lots to remember
|
|
|
|
## Text Analysis
|
|
- Train sequences of text character-by-character
|
|
- Maintains state vector representing data up to current token
|
|
- Combines state vector with next token to create new vector
|
|
- In theory, info from one token can propagate arbitrarily far down the sequence
|
|
- In practice suffers from vanishing gradient
|
|
- Can't extract precise information about previous tokens
|
|
|
|
![[rnn-input.png]]
|
|
![[rnn-recurrence.png]] |