♎
Limited AI
  • Machine Learning
    • Linear Model Cheating Sheet
    • Nonlinear Model Cheating Sheet
    • General Linear Model 1
    • General Linear Model 2
    • General Linear Model 3
    • Tree Based Methods
    • Tree Based Methods Supplement
    • XG,Cat,Light__Boosting
    • KNN&PCA
    • Model Performance
    • Model Evaluation
    • Code Practice
      • KNN
      • Decision Tree Python Code
    • Data and Feature Engineering
      • Handle Bias Data
      • Cold Start Problem
  • Deep Learning
    • Summary v2
    • Basic Neural Network
      • From Linear to Deep
      • Perceptron and Activation Function
      • NN network Details
      • Backpropagation Details
      • Gradient Vanishing vs Gradient Exploding
    • Basic CNN
      • Why CNN
      • Filter/ Convolution Kernel and Its Operation
      • Padding& Stride
      • Layers
      • Extra:From Fully Connected Layers to Convolutions
      • Extra: Multiple Input and Multiple Output Channels
    • Advance CNN
      • Convolutional Neural Networks(LeNet)
      • Deep Convolution Neural Networks(AlexNet)
      • Networks Using Blocks (VGG)
      • Network in Network(NiN)
      • Multi-Branch Networks(GoogLeNet&I mageNet)
      • Residual Networks(ResNet) and ResNeXt
      • Densely Connected Networks(DenseNet)
      • Batch Normalization
    • Basic RNN
      • Seq Model
      • Raw Text to Seq
      • Language Models
      • Recurrent Neural Networks(RNN)
      • Backpropagation Through Time
    • Advance RNN
      • Gated Recurrent Units(GRU)
      • Long Short-Term Memory(LSTM)
      • Bidirectional Recurrent Neural Networks(BRNN)
      • Encoder-Decoder Architecture
      • Seuqence to Sequence Learning(Seq2Seq)
    • Attention Mechanisms and Transformers
      • Queries, Keys, and Values
      • Attention is all you need
        • Attention and Kernel
        • Attention Scoring Functions
        • The Bahdanau Attention Mechanism
        • Multi-Head Attention
        • Self-Attention
        • Attention的实现
      • The Transformer Architecture
        • Extra Reading
        • 最短的最大路径长度
      • Large-Scaling Pretraning with Transformers
        • BERT vs OpenAI GPT vs ELMo
        • Decoder Model框架
        • Bert vs XLNet
        • T5& GPT& Bert比较
        • 编码器-解码器架构 vs GPT 模型
        • Encoder vs Decoder Reference
      • Transformers for Vision
      • Transformer for Multiomodal
    • NLP Pretraining
      • Word Embedding(word2vec)
        • Extra Reading
      • Approximate Training
      • Word Embedding with Global Vectors(GloVe)
        • Extra Reading
        • Supplement
      • Encoder(BERT)
        • BERT
        • Extra Reading
      • Decoder(GPT&XLNet&Lamma)
        • GPT
        • XLNet
          • XLNet架构
          • XLNet特点与其他比较
      • Encoder-Decoder(BART& T5)
        • BART
        • T5
  • GenAI
    • Introduction
      • GenAI Paper Must Read
      • GenAI六个阶段
    • Language Models Pre-training
      • Encoder-Decoder Architecture
      • Encoder Deep Dive
      • Decoder Deep Dive
      • Encoder VS Decoder
      • Attention Mechanism
      • Transformers
    • Example: Llama 3 8B架构
    • Fine-Tuning Generation Models
    • RAG and Adavance RAG
    • AI Agent
  • Statistics and Optimization
    • A/B testing
    • Sampling/ABtesting/GradientMethod
    • Gradient Decent Deep Dive
  • Machine Learning System Design
    • Extra Reading
    • Introduction
  • Responsible AI
    • AI Risk and Uncertainty
      • What is AI risk
      • General Intro for Uncertainty Quantification
      • Calibration
      • Conformal Prediction
        • Review the linear regression
        • Exchangeability
        • Split Conformal Prediction
        • Conformalized Quantile Regression
        • Beyond marginal coverage
        • Split Conformal Classification
        • Full Conformal Coverage
        • Cross-Validation +
        • Conformal Histgram Regression
    • xAI
      • SHAP value
  • Extra Research
    • Paper Reading
    • Reference
Powered by GitBook
On this page
  1. Deep Learning
  2. Attention Mechanisms and Transformers
  3. Attention is all you need

The Bahdanau Attention Mechanism

PreviousAttention Scoring FunctionsNextMulti-Head Attention

Last updated 8 months ago

我们之前提到过，透过基于两个RNN的encoder-decoder的架构，用于序列到序列的学习

  • RNN可以将长度可变的序列转换为固定形状的上下文变量，然后透过RNN根据生成的词元和上下文变量，按词元生成输出（目标）序列词元

  • 然而，即使并非所有的输入（源）词元都对某个解码某个词元都有用，在每个解码步骤中仍然使用编码上下文变量

那有什么方法可以改变上下文变量呢

  • Bahdanau等人提出了一个没有严格单向对齐限制的可微注意力模型。

  • 在预测词元时，如果不是所有输入词元都相关，模型将仅对齐（或参与）输入序列中与当前预测相关的部分。

  • 这是通过将上下文变量视为注意力集中的输出来实现

模型

下面描述的Bahdanau注意力模型将遵循前面encoder-decoder中的相同符号表述。这个新的基于注意力的模型与前面中的模型相同，只不过前文中的上下文变量 ccc 在任何解码时刻t′t't′都会被 ct′c_{t'}ct′​ 替换。假设输入序列中有 TTT 个词元，解码时刻 t′t't′ 的上下文变量是注意力集中输出：

ct′=∑t=1Tα(st′−1,ht)htc_{t'} = \sum_{t=1}^{T} \alpha(s_{t'-1}, h_t) h_tct′​=∑t=1T​α(st′−1​,ht​)ht​

其中，时刻 t′−1t' - 1t′−1 时的解码器隐层状态 st′−1s_{t'-1}st′−1​ 是查询，编码器隐状态 hth_tht​ 既是键，也是值，注意力权重 α\alphaα 是使用前面所定义的加性注意力打分函数计算的，以下描述了Bahdanau注意力的架构：