Deep Learning for NLP: Memory-based Networks
Natural Language Processing
| Intermediate
- 12 videos | 1h 27m 5s
- Includes Assessment
- Earns a Badge
In the journey to understand deep learning models for natural language processing (NLP), the subsequent iterations are memory-based networks, which are much more capable of handling extended context in languages. While basic neural networks are better than machine learning (ML) models, they still lack in more significant and large language data problems. In this course, you will learn about memory-based networks like gated recurrent unit (GRU) and long short-term memory (LSTM). Explore their architectures, variants, and where they work and fail for NLP. Then, consider their implementations using product classification data and compare different results to understand each architecture's effectiveness. Upon completing this course, you will have learned the basics of memory-based networks and their implementation in TensorFlow to understand the effect of memory and more extended context for NLP datasets.
WHAT YOU WILL LEARN
-
Discover the key concepts covered in this course
Outline the importance of memory-based learning and the different networks it supports
Outline gated recurrent unit (gru) and how it differs from recurrent neural networks (rnns)
Outline long short-term memory (lstm) networks and how they differ from rnn
Illustrate how lstm networks work better and solve the vanishing gradient problem
Illustrate different types of lstm networks -
Perform data preparation for lstm and gru networks
Perform review classification using gru
Perform review classification using lstm
Perform review classification using bidirectional long short-term memory (bi-lstm)
Compare results of important features across different networks
Summarize the key concepts covered in this course
IN THIS COURSE
-
1m 17s
-
4m 28sIn this video, you will outline the importance of memory-based learning and the different types of memory it supports. FREE ACCESS
-
3. Gated Recurrent Unit (GRU) Architecture9m 9sIn this video, you will outline a gated recurrent unit (GRU) and how it differs from recurrent neural networks (RNNs). FREE ACCESS
-
4. Long Short-term Memory (LSTM) Architecture8m 40sIn this video, you will outline long short-term memory (LSTM) networks and how they differ from traditional recurrent neural networks (RNNs). FREE ACCESS
-
5. Fall of RNN versus Rise of LSTM1m 53sAfter completing this video, you will be able to illustrate how LSTM networks work better and solve the vanishing gradient problem. FREE ACCESS
-
6. Variants of LSTM networks4m 39sUpon completion of this video, you will be able to illustrate different types of LSTM networks. FREE ACCESS
-
7. Product Review Data Preparation for Modeling10m 35sIn this video, learn how to prepare data for LSTM and GRU networks. FREE ACCESS
-
8. Product Review Data Classification Using GRU10m 16sLearn how to classify reviews using GRU. FREE ACCESS
-
9. Product Review Data Classification Using LSTM10m 58sFind out how to classify reviews using LSTM. FREE ACCESS
-
10. Product Review Data Classification Using Bi-LSTM12m 9sLearn how to classify reviews using bidirectional long short-term memory (Bi-LSTM). FREE ACCESS
-
11. Result Comparison between RNN, GRU, and LSTM11m 35sLearn how to compare the results of important features across different networks. FREE ACCESS
-
12. Course Summary1m 26s
EARN A DIGITAL BADGE WHEN YOU COMPLETE THIS COURSE
Skillsoft is providing you the opportunity to earn a digital badge upon successful completion on some of our courses, which can be shared on any social network or business platform.
Digital badges are yours to keep, forever.YOU MIGHT ALSO LIKE
