explanation
Deep Learning LiveLessons for Natural Language Processing, 2nd Edition is an introductory course to natural language processing using TensorFlow-Keras deep learning models. This course introduces how to build a natural language learning model using deep learning. This course will give you an intuitive explanation of theoretical topics along with working with Jupyter notebooks.
Here’s what you’ll learn in this Deep Learning LiveLessons (video training) course for natural language processing:
- Natural language data preprocessing used in machine learning applications
- Convert natural language to numeric mode using word2vec
- Make predictions using deep learning models trained using natural language
- Utilize the latest natural language learning technology using Keras
- Optimize the efficiency of deep learning models by choosing an appropriate model architecture and quantifying model hyperparameters.
Course specifications
Posted by InformIT
teacher: john crone
Language:English
Learning level: Medium
Number of courses: 34
Duration: 4 hours 59 minutes
Course Topics:
introduction
Lesson 1: The Power and Elegance of Deep Learning for NLP
subject
1.1 Introduction to deep learning for natural language processing
1.2 Running hands-on code examples in Jupyter Notebook
1.3 Review of prerequisites for deep learning theory
1.4 Preview
Lesson 2: Word Vectors
subject
2.1 Computational representation of natural language elements
2.2 Visualizing word vectors with word2viz
2.3 Localism vs. Decentralized Representation
2.4 Elements of natural human language
2.5 word2vec algorithm
2.6 Creating word vectors using word2vec
2.7 Pre-trained word vectors and doc2vec
Lesson 3: Modeling Natural Language Data
subject
3.1 Best practices for natural language data preprocessing
3.2 Area under ROC curve
3.4 Document classification using dense neural networks
3.5 Classification using convolutional neural networks
Lesson 4: Recurrent Neural Networks
subject
4.1 Essential theory of RNN
4.2 Real RNNs
4.3 Essential theories of LSTM and GRU
4.4 Real LSTM and GRU
Unit 5: Advanced Models
subject
5.1 Bidirectional LSTM
5.2 Stacked LSTM
5.3 Datasets for NLP
5.4 Sequence creation
5.5 seq2seq and cautions
5.6 Transfer learning in NLP: BERT, ELMo, GPT-2 and other characters
5.7 Out-of-order architecture: API
5.8 (Financial) Time Series Applications
summary
Course Prerequisites:
author’s Deep learning with TensorFlow, Keras, and PyTorch LiveLesson or knowledge of the topics covered in chapters 5 through 9 of his book. Deep learning example This is a prerequisite.
movie
sample film
installation manual
After extracting, watch with your favorite players.
Subtitles: None
Quality: 720p
download link
File password: free download software
size
8.3GB