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
1.4 KiB
1.4 KiB
- Attention
- Weighting significance of parts of the input
- Including recursive output
- Weighting significance of parts of the input
- Similar to RNNs
- Process sequential data
- Translation & text summarisation
- Differences
- Process input all at once
- Largely replaced LSTM and gated recurrent units (GRU) which had attention mechanics
- No recurrent structure
Examples
- BERT
- Bidirectional Encoder Representations from Transformers
- Original GPT
transformers-explained-visually-part-1-overview-of-functionality
Architecture
Input
- Byte-pair encoding tokeniser
- Mapped via word embedding into vector
- Positional information added
Encoder/Decoder
- Similar to seq2seq models
- Create internal representation
- Encoder layers
- Create encodings that contain information about which parts of input are relevant to each other
- Subsequent encoder layers receive previous encoding layers output
- Decoder layers
- Takes encodings and does opposite
- Uses incorporated textual information to produce output
- Has attention to draw information from output of previous decoders before drawing from encoders
- Both use attention
- Both use dense layers for additional processing of outputs
- Contain residual connections & layer norm steps