/DeepLearning-NLP

Introduction to Deep Learning for Natural Language Processing

Primary LanguageJupyter NotebookMIT LicenseMIT

Introduction to Deep Learning for Natural Language Processing

This repo accompanies the Introduction to Deep Learning for Natural Language Processing workshop to explain the core concepts of deep learning with emphasis on classifying text as the application. Python data stack is used for the workshop.

Overview

The following topics are covered

  1. What is deep learning?
  2. Motivation: Some use cases
  3. Building blocks of Neural Networks (Neuron, Activation Function, Backpropagation Algorithm)
  4. Word Embedding
  5. word2vec
  6. Introduction to keras
  7. Multi-layer perceptron
  8. Convolutional Neural Network
  9. Recurrent Neural Network
  10. Challenges in Deep Learning

Depending on time, the following topics might be covered

  1. Using tensorflow as backend for keras
  2. Unsupervised learning using Autoencoders

Installation Instructions

Please refer to the installation instructions document. That document also has instructions on how to run a script to check if the required packages are installed.

Slides

The slides used for the workshop are available here