Duration
28 hours (usually 4 days including breaks)
Requirements
- An understanding of Python programming
- An understanding of Python libraries in general
Audience
- Programmers with interest in linguistics
- Programmers who seek an understanding of NLP (Natural Language Processing)
Overview
DL (Deep Learning) is a subset of ML (Machine Learning).
Python is a popular programming language that contains libraries for Deep Learning for NLP.
Deep Learning for NLP (Natural Language Processing) allows a machine to learn simple to complex language processing. Among the tasks currently possible are language translation and caption generation for photos.
In this instructor-led, live training, participants will learn to use Python libraries for NLP as they create an application that processes a set of pictures and generates captions.
By the end of this training, participants will be able to:
- Design and code DL for NLP using Python libraries.
- Create Python code that reads a substantially huge collection of pictures and generates keywords.
- Create Python Code that generates captions from the detected keywords.
Format of the course
- Part lecture, part discussion, exercises and heavy hands-on practice
Course Outline
Introduction to Deep Learning for NLP
Differentiating between the various types of DL models
Using pre-trained vs trained models
Using word embeddings and sentiment analysis to extract meaning from text
How Unsupervised Deep Learning works
Installing and Setting Up Python Deep Learning libraries
Using the Keras DL library on top of TensorFlow to allow Python to create captions
Working with Theano (numerical computation library) and TensorFlow (general and linguistics library) to use as extended DL libraries for the purpose of creating captions.
Using Keras on top of TensorFlow or Theano to quickly experiment on Deep Learning
Creating a simple Deep Learning application in TensorFlow to add captions to a collection of pictures
Troubleshooting
A word on other (specialized) DL frameworks
Deploying your DL application
Using GPUs to accelerate DL
Closing remarks