Deep Learning Specialization - Coursera
main
main
  • Introduction
  • Neural Networks and Deep Learning
    • Introduction to Deep Learning
    • Logistic Regression as a Neural Network (Neural Network Basics)
    • Shallow Neural Network
    • Deep Neural Network
  • Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
    • Practical Aspects of Deep Learning
    • Optimization Algorithms
    • Hyperparameter Tuning, Batch Normalization and Programming Frameworks
  • Structuring Machine Learning Projects
    • Introduction to ML Strategy
    • Setting Up Your Goal
    • Comparing to Human-Level Performance
    • Error Analysis
    • Mismatched Training and Dev/Test Set
    • Learning from Multiple Tasks
    • End-to-End Deep Learning
  • Convolutional Neural Networks
    • Foundations of Convolutional Neural Networks
    • Deep Convolutional Models: Case Studies
      • Classic Networks
      • ResNets
      • Inception
    • Advice for Using CNNs
    • Object Detection
      • Object Localization
      • Landmark Detection
      • Sliding Window Detection
      • The YOLO Algorithm
      • Intersection over Union
      • Non-Max Suppression
      • Anchor Boxes
      • Region Proposals
    • Face Recognition
      • One-Shot Learning
      • Siamese Network
      • Face Recognition as Binary Classification
    • Neural Style Transfer
  • Sequence Models
    • Recurrent Neural Networks
      • RNN Structure
      • Types of RNNs
      • Language Modeling
      • Vanishing Gradient Problem in RNNs
      • Gated Recurrent Units (GRUs)
      • Long Short-Term Memory Network (LSTM)
      • Bidirectional RNNs
    • Natural Language Processing & Word Embeddings
      • Introduction to Word Embeddings
      • Learning Word Embeddings: Word2Vec and GloVe
      • Applications using Word Embeddings
      • De-Biasing Word Embeddings
    • Sequence Models & Attention Mechanisms
      • Sequence to Sequence Architectures
        • Basic Models
        • Beam Search
        • Bleu Score
        • Attention Model
      • Speech Recognition
Powered by GitBook
On this page

Was this helpful?

  1. Sequence Models
  2. Sequence Models & Attention Mechanisms
  3. Sequence to Sequence Architectures

Attention Model

As previously discussed, an encoder-decoder RNN was used to perform machine translation. It would first memorize the entire input sentence and generate an encoding, which would then be decoded by the decoder part of the network.

However, the performance of such an architecture is not good when it comes to long sentences, say >30-40 words.

In such cases, the attention model is more accurate. It works on the idea of translating a sentence part by part, like the human brain does. It helps to determine how much attention has to be given to a given part of the input, while generating the translation.

Apart from machine translation, the attention mechanism can also be used for applications such as image captioning, i.e. generating a caption by looking at the image one part at a time.

It can also be used for speech recognition.

PreviousBleu ScoreNextSpeech Recognition

Last updated 4 years ago

Was this helpful?