Tensorflow: Word Embeddings & Recurrent Neural Networks


Overview/Description
Expected Duration
Lesson Objectives
Course Number
Expertise Level



Overview/Description

Explore how to model language and text with word embeddings and how to use those embeddings in Recurrent Neural Networks. Leveraging TensorFlow to build custom RNN models is also covered.



Expected Duration (hours)
0.7

Lesson Objectives

Tensorflow: Word Embeddings & Recurrent Neural Networks

  • Course Overview
  • perform text to numeric conversion using one-hot encoding
  • use frequency-based methods to generate word embeddings
  • use name prediction-based methods to generate word embeddings
  • identify pre-trained models for word vector embeddings
  • describe how to work with recurrent neurons
  • recognize the construction of a recurrent neural networks by unrolling recurrent memory cells
  • recognize the forward and backward passes while training a recurrent neural network
  • compare long memory cells with the normal recurrent neuron
  • "describe different kinds of encodings and why they are used "
  • describe the working of recurrent neural networks and how they differ from regular neural networks
  • Course Number:
    it_sdaidt_09_enus

    Expertise Level
    Intermediate