Deep Learning for NLP: Neural Network Architectures

Natural Language Processing    |    Intermediate
  • 19 Videos | 2h 30m 10s
  • Includes Assessment
  • Earns a Badge
Natural language processing (NLP) is constantly evolving with cutting edge advancements in tools and approaches. Neural network architecture (NNA) supports this evolution by providing a method of processing language-based information to solve complex data-driven problems. Explore the basic NNAs relevant to NLP problems. Learn different challenges and use cases for single-layer perceptron, multi-layer perceptron, and RNNs. Analyze data and its distribution using pandas, graphs, and charts. Examine word vector representations using one-hot encodings, Word2vec, and GloVe and classify data using recurrent neural networks. After you have completed this course, you will be able to use a product classification dataset to implement neural networks for NLP problems.

WHAT YOU WILL LEARN

  • discover the key concepts covered in this course
    illustrate single layer perceptron architecture of a neural network
    illustrate MLP Architecture of Neural Network
    describe RNN Architecture and how it can capture context in language
    describe the various challenges of RNN
    illustrate different applications of basic Neural Network-based architecture
    describe the Amazon Product Reviews dataset and list the libraries that are required to be imported
    describe the steps to load the Amazon Product Reviews dataset into Google Colaboratory
    explore the data and its distribution in the Amazon Product Reviews dataset
    analyze the product review data using pandas, graphs, and charts
  • describe the steps involved in pre-processing the product review dataset
    illustrate word representations using one-hot encodings
    illustrate word vector representations using neural network and Word2vec
    create average feature vectors of all the words in the word vector
    create word embeddings vector using Word2vec
    construct a RNN model with Word2Vec Embeddings
    illustrate sentence vector representations using GloVe vectors
    perform classification of product review data using RNN
    summarize the key concepts covered in this course

IN THIS COURSE

  • Playable
    1. 
    Course Overview
    1m 19s
    UP NEXT
  • Playable
    2. 
    Basic Architecture of a Neural Network
    4m 10s
  • Locked
    3. 
    Multilayer Perceptron (MLP)
    2m 48s
  • Locked
    4. 
    Recurrent Neural Network (RNN) Architecture
    5m 5s
  • Locked
    5. 
    Challenges in RNN
    3m 19s
  • Locked
    6. 
    Applications of Neural Network-based Architecture
    1m 5s
  • Locked
    7. 
    Introducing the Product Reviews Data
    11m 55s
  • Locked
    8. 
    Loading Product Reviews Data into Google Colaboratory
    6m 55s
  • Locked
    9. 
    Understanding Product Reviews Data
    15m 45s
  • Locked
    10. 
    Exploring Product Reviews Data
    12m 40s
  • Locked
    11. 
    Pre-processing Product Reviews Data
    7m 39s
  • Locked
    12. 
    Applying Feature Engineering - Word Representation
    9m 54s
  • Locked
    13. 
    Creating Vector Representations Using Word2vec
    15m 14s
  • Locked
    14. 
    Averaging Feature Vectors
    13m 19s
  • Locked
    15. 
    Creating Word Embeddings with Word2Vec
    11m 6s
  • Locked
    16. 
    Constructing a RNN Model with Word2vec Embeddings
    8m 19s
  • Locked
    17. 
    Using GloVe Vectors
    11m 10s
  • Locked
    18. 
    Product Reviews Classification Using RNN
    7m 7s
  • Locked
    19. 
    Course Summary
    1m 24s

EARN A DIGITAL BADGE WHEN YOU COMPLETE THIS COURSE

Skillsoft is providing you the opportunity to earn a digital badge upon successful completion of this course, which can be shared on any social network or business platform

Digital badges are yours to keep, forever.