♎
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
  • 大纲
  • Transformer Family Summary
  1. Deep Learning

Attention Mechanisms and Transformers

PreviousSeuqence to Sequence Learning(Seq2Seq)NextQueries, Keys, and Values

Last updated 8 months ago

大纲

  • 首先回顾一个经典注意力框架，解释如何在视觉场景中展开注意力。 受此框架中的注意力提示（attention cues）的启发， 我们将设计能够利用这些注意力提示的模型。 1964年的Nadaraya-Waston核回归（kernel regression）正是具有 注意力机制（attention mechanism）的机器学习的简单演示。

  • 然后继续介绍的是注意力函数，它们在深度学习的注意力模型设计中被广泛使用。 具体来说，我们将展示如何使用这些函数来设计Bahdanau注意力。 Bahdanau注意力是深度学习中的具有突破性价值的注意力模型，它双向对齐并且可以微分。

  • 最后将描述仅仅基于注意力机制的Transformer架构， 该架构中使用了多头注意力（multi-head attention） 和自注意力（self-attention）。 自2017年横空出世，Transformer一直都普遍存在于现代的深度学习应用中， 例如语言、视觉、语音和强化学习领域。

Transformer Family Summary

Reference

  • ， 他的slide很不错

  • 和前面类似的讲义

  • 国内讲的还行的

https://huggingface.co/docs/transformers/en/model_summary
https://datawhalechina.github.io/learn-nlp-with-transformers/#/./%E7%AF%87%E7%AB%A02-Transformer%E7%9B%B8%E5%85%B3%E5%8E%9F%E7%90%86/2.3-%E5%9B%BE%E8%A7%A3BERT
https://github.com/datawhalechina/leedl-tutorial
https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1244/slides/cs224n-2024-lecture08-transformers.pdf
https://www.youtube.com/watch?v=wzfWHP6SXxY&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4&index=7
https://udlbook.github.io/udlbook/
https://www.borealisai.com/research-blogs/tutorial-14-transformers-i-introduction/
https://blog.csdn.net/hy592070616/article/details/131361891