Natural Language Processing(NLP) with Deep Learning in Keras
4.3 (102 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
813 students enrolled

Natural Language Processing(NLP) with Deep Learning in Keras

Word2Vec, Glove, FastText, Universal Sentence Encoder, GRU, LSTM, Conv-1D, Seq2Seq, Machine Translation and much more!
4.3 (102 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
813 students enrolled
Created by CARLOS QUIROS
Last updated 7/2019
English
English [Auto]
Current price: $135.99 Original price: $194.99 Discount: 30% off
5 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 8.5 hours on-demand video
  • 2 articles
  • 7 downloadable resources
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • Upgrade the knowledge of Natural Language Processing using Deep Learning models
Course content
Expand all 45 lectures 08:18:59
+ Installation and Setup
5 lectures 24:45
Before starting read these important guidelines!!
02:05
Resources: Codes, Datasets, Papers and more
00:13
Installing TensorFlow for CPU/GPU/Cuda and Keras
09:49
+ Deep Learning Overview
9 lectures 01:24:46
Deep Learning Concept
10:48
Gradient Descent
14:02
Vanishing and Exploding Gradients
06:13
Beyond Gradient Descent
11:29
Loss Functions
06:49
Activation Functions
10:13
Dropout
07:13
Batch Normalization
07:01
Convolutional Layers
10:58
+ Deep Learning for NLP
23 lectures 04:43:03
Introduction
01:49
Word Embeddings on Sentiment Analysis
16:20
Visualizing Word Embeddings
06:52
Word2Vec Model
18:01
Word2Vec-Skipgrams-Keras
14:21
Word2Vec-CBOW-Keras
14:11
The GloVe model
14:18
Yelp Comments Classification with GloVe part 1
09:55
Yelp Comments Classification with GloVe part 2
12:33
FastText model
06:48
FastText with Gensim
11:55
FastText on Google Collaboratory
17:57
RNN-GRU-LSTM models
18:50
Sentiment Analysis with GRU, CuDNNGRU, LSTM, CuDNNLSTM-part 1
11:49
Sentiment Analysis with GRU, CuDNNGRU, LSTM, CuDNNLSTM-part 2
08:53
1D Convolutional Layer for NLP
09:15
Sentiment Analysis with 1D ConvNet part 1
12:38
Sentiment Analysis with 1D ConvNet part 2
10:17
Seq2Seq and the Attention Mechanism
17:19
Encoder-Decoder with Attention
16:39
Universal Sentence Encoder
10:04
Semantic Similarity with TF-Hub Universal Encoder
08:22
Text Classification with TF-Hub Universal Encoder
13:57
+ Applications
8 lectures 01:46:25
Text Generation
16:13
Emotion recognition with LSTM and Attention part 2
15:35
Emotion recognition with LSTM and Attention part 1
07:56
Neural Machine Translation with Seq2Seq
18:37
Improving Neural Machine Translation part 2
12:23
Improving Neural Machine Translation part 1
10:53
Developing a Chat Bot part 1
13:01
Developing a Chat Bot part 2
11:47
Requirements
  • Machine Learning, NLP basics, Linear Algebra, Python, Tensor Flow, Keras
Description

Natural Language Processing (NLP) is a hot topic into Machine Learning field. 

This course is an advanced course of NLP using Deep Learning approach. Before starting this course please read the guidelines of the lesson 2 to have the best experience in this course.

This course starts with the configuration and the installation of all resources needed including the installation of Tensor Flow CPU/GPU, Cuda and Keras. You will be able to use your GPU card if you have one, to accelate so fast the processes. But if you dont have a GPU card you can follow the instructions for running the standard CPU code, it will take a while but you still can run it.

After that we are going to review the main concepts of Deep Learning in the Chapter 2 for applying them into the Natural Language Processing field offering you a solid background for the main chapter.

In the main Chapter 3 we are going to study the main Deep Learning libraries and models for NLP such as Word Embeddings, Word2Vec, Glove, FastText, Universal Sentence Encoder, RNN, GRU, LSTM, Convolutions in 1D, Seq2Seq, Memory Networks, and the Attention mechanism.

This course offers you many examples, with different datasets suchs as Google News, Yelp comments, Amazon reviews, IMDB reviews, the Bible corpus, etc and different text corpus. At the final in Chapter 4 you will put in practice your knowledge with practical applications such as Multiclass Sentiment Analysis, Text Generation, Machine Translation, Developing a ChatBot and more. 

For coding we are going to use TensorFlow, Keras, Google Colab and many Python libraries.


If you need a previous background in Natural Language Processing or in Machine Learning I recommend you my courses:

  • Python for Machine Learning and Data Mining  or 

  • Natural Language Processing with Python and NLTK

Who this course is for:
  • Professionals looking for an advanced course of Natural Language Processing using Deep Learning approach