InformIT – Deep Learning for Natural Language Processing LiveLessons (Video Training), 2nd Edition 2020-2

Published on: 2021-10-27 21:12:26

Categories: 28

Description

Deep Learning for Natural Language Processing LiveLessons (Video Training), 2nd Edition, is an introductory course for natural language processing using TensorFlow-Keras deep learning models. This course is an introduction to building natural language learning models using in-depth learning. With this course, you will gain an intuitive explanation of theoretical topics along with working with the Jupyter notebook.

What you will learn in the Deep Learning for Natural Language Processing LiveLessons (Video Training) course:

Pre-processing natural language data used in machine learning applications
Transform natural language into numeric mode using word2vec
Perform predictions using deep learning models taught using natural language
Using the latest natural language learning technologies using Keras
Optimizing the efficiency of deep learning models by selecting the appropriate model architecture and quantifying the model hyperparameters

Course specifications

Publisher: InformIT
Instructors: Jon Krohn
Language: English
Learning Level: Medium
Number of Courses: 34
Duration: 4 hours and 59 minutes

Course topics:

Introduction
Lesson 1: The Power and Elegance of Deep Learning for NLP
Topics
1.1 Introduction to Deep Learning for Natural Language Processing
1.2 Running the Hands-On Code Examples in Jupyter Notebooks
1.3 Review of Prerequisite Deep Learning Theory
1.4 A Sneak Peek

Lesson 2: Word Vectors
Topics
2.1 Computational Representations of Natural Language Elements
2.2 Visualizing Word Vectors with word2viz
2.3 Localist Versus Distributed Representations
2.4 Elements of Natural Human Language
2.5 The word2vec Algorithm
2.6 Creating Word Vectors with word2vec
2.7 Pre-Trained Word Vectors and doc2vec

Lesson 3: Modeling Natural Language Data
Topics
3.1 Best Practices for Preprocessing Natural Language Data
3.2 The Area Under the ROC Curve
3.4 Document Classification with a Dense Neural Net
3.5 Classification with a Convolutional Neural Net

Lessons 4: Recurrent Neural Networks
Topics
4.1 Essential Theory of RNNs
4.2 RNNs in Practice
4.3 Essential Theory of LSTMs and GRUs
4.4 LSTMs and GRUs in Practice

Lesson 5: Advanced Models
Topics
5.1 Bi-Directional LSTMs
5.2 Stacked LSTMs
5.3 Datasets for NLP
5.4 Sequence Generation
5.5 seq2seq and Attention
5.6 Transfer Learning in NLP: BERT, ELMo, GPT-2 and Other Characters
5.7 Non-Sequential Architectures: API
5.8 (Financial) Time Series Applications

Summary

Course prerequisites:

The author’s Deep Learning with TensorFlow, Keras, and PyTorch LiveLessons , or familiarity with the topics covered in Chapters 5 through 9 of his book Deep Learning Illustrated , are a prerequisite.