Sequence Models

Sequence Models

This course is part of Deep Learning Specialization

Instructors: Andrew Ng

Top Instructor

Access provided by Aditya Birla Group

458,086 already enrolled

4 modules

Gain insight into a topic and learn the fundamentals.

31,233 reviews

Intermediate level

Recommended experience

Flexible schedule

4 weeks at 10 hours a week

Learn at your own pace

94%

Most learners liked this course

4 modules

Gain insight into a topic and learn the fundamentals.

31,233 reviews

Intermediate level

Recommended experience

Flexible schedule

4 weeks at 10 hours a week

Learn at your own pace

94%

Most learners liked this course

Skills you'll gain

Tools you'll learn

Hugging Face

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

4 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your subject-matter expertise

This course is part of the Deep Learning Specialization

When you enroll in this course, you'll also be enrolled in this Specialization.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate

There are 4 modules in this course

In the fifth course of the Deep Learning Specialization, you will become familiar with sequence models and their exciting applications such as speech recognition, music synthesis, chatbots, machine translation, natural language processing (NLP), and more.

By the end, you will be able to build and train Recurrent Neural Networks (RNNs) and commonly-used variants such as GRUs and LSTMs; apply RNNs to Character-level Language Modeling; gain experience with natural language processing and Word Embeddings; and use HuggingFace tokenizers and transformer models to solve different NLP tasks such as NER and Question Answering. The Deep Learning Specialization is a foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. It provides a pathway for you to take the definitive step in the world of AI by helping you gain the knowledge and skills to level up your career.

Discover recurrent neural networks, a type of model that performs extremely well on temporal data, and several of its variants, including LSTMs, GRUs and Bidirectional RNNs,

What's included

12 videos5 readings1 assignment3 programming assignments

12 videos Total 112 minutes

Why Sequence Models? 3 minutes
Notation 9 minutes
Recurrent Neural Network Model 17 minutes
Backpropagation Through Time 6 minutes
Different Types of RNNs 10 minutes
Language Model and Sequence Generation 12 minutes
Sampling Novel Sequences 9 minutes
Vanishing Gradients with RNNs 6 minutes
Gated Recurrent Unit (GRU) 17 minutes
Long Short Term Memory (LSTM) 10 minutes
Bidirectional RNN 8 minutes
Deep RNNs 5 minutes

5 readings Total 10 minutes

Join the DeepLearning.AI Forum to ask questions, get support, or share amazing ideas! 2 minutes
Clarifications about Upcoming Gated Recurrent Unit (GRU) Video 1 minute
Clarifications about Upcoming Long Short Term Memory (LSTM) Video 1 minute
Lecture Notes W1 1 minute
(Optional) Downloading your Notebook, Downloading your Workspace and Refreshing your Workspace 5 minutes

1 assignment Total 50 minutes

Recurrent Neural Networks 50 minutes

3 programming assignments Total 540 minutes

Building your Recurrent Neural Network - Step by Step 180 minutes
Dinosaur Island-Character-Level Language Modeling 180 minutes
Jazz Improvisation with LSTM 180 minutes

Natural language processing with deep learning is a powerful combination. Using word vector representations and embedding layers, train recurrent neural networks with outstanding performance across a wide variety of applications, including sentiment analysis, named entity recognition and neural machine translation.

What's included

10 videos2 readings1 assignment2 programming assignments

10 videos Total 99 minutes

Word Representation 10 minutes
Using Word Embeddings 9 minutes
Properties of Word Embeddings 11 minutes
Embedding Matrix 4 minutes
Learning Word Embeddings 10 minutes
Word2Vec 13 minutes
Negative Sampling 12 minutes
GloVe Word Vectors 11 minutes
Sentiment Classification 8 minutes
Debiasing Word Embeddings 11 minutes

2 readings Total 2 minutes

Clarifications about Upcoming GloVe Word Vectors Video 1 minute
Lecture Notes W2 1 minute

1 assignment Total 50 minutes

Natural Language Processing & Word Embeddings 50 minutes

2 programming assignments Total 360 minutes

Operations on Word Vectors - Debiasing 180 minutes
Emojify 180 minutes

Augment your sequence models using an attention mechanism, an algorithm that helps your model decide where to focus its attention given a sequence of inputs. Then, explore speech recognition and how to deal with audio data.

What's included

10 videos2 readings1 assignment2 programming assignments

10 videos Total 98 minutes

Basic Models 6 minutes
Picking the Most Likely Sentence 9 minutes
Beam Search 12 minutes
Refinements to Beam Search 10 minutes
Error Analysis in Beam Search 10 minutes
Bleu Score (Optional) 16 minutes
Attention Model Intuition 10 minutes
Attention Model 12 minutes
Speech Recognition 9 minutes
Trigger Word Detection 5 minutes

2 readings Total 11 minutes

Clarifications about Upcoming Attention Model Video 10 minutes
Lecture Notes W3 1 minute

1 assignment Total 50 minutes

Sequence Models & Attention Mechanism 50 minutes

2 programming assignments Total 360 minutes

Neural Machine Translation 180 minutes
Trigger Word Detection 180 minutes

What's included

5 videos5 readings1 assignment1 programming assignment3 ungraded labs

5 videos Total 42 minutes

Transformer Network Intuition 5 minutes
Self-Attention 12 minutes
Multi-Head Attention 8 minutes
Transformer Network 14 minutes
Conclusion and Thank You! 3 minutes

5 readings Total 33 minutes

Lecture Notes W4 1 minute
[IMPORTANT] Reminder about end of access to Lab Notebooks 2 minutes
References 10 minutes
Acknowledgments 10 minutes
(Optional) Opportunity to Mentor Other Learners 10 minutes

1 assignment Total 50 minutes

Transformers 50 minutes

1 programming assignment Total 180 minutes

Transformers Architecture with TensorFlow 180 minutes

3 ungraded labs Total 180 minutes

Transformer Pre-processing 60 minutes
Transformer Network Application: Named-Entity Recognition 60 minutes
Transformer Network Application: Question Answering 60 minutes

Earn a career certificate

Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.

Instructors

Instructor ratings

(2,846 ratings)

Top Instructor

Andrew Ng

DeepLearning.AI

51 Courses 9,650,446 learners

Offered by

DeepLearning.AI

Why people choose Coursera for their career

Felipe M.

Learner since 2018

"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."

Jennifer J.

Learner since 2020

"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."

Larry W.

Learner since 2021

"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."

Chaitanya A.

"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

Learner reviews

5 stars
83.76%
4 stars
12.88%
3 stars
2.56%
2 stars
0.47%
1 star
0.31%

Showing 3 of 31233

Reviewed on Jul 14, 2021

the assignments were a really good format for someone who hasn't learned how to derive wrt multiple variables. It made sense to have the formulas provided to introduce a context for me: a developer.

Reviewed on Mar 30, 2020

It's an exciting course to learn about sequence models. The assignment illustrate the concept via step by step to understand how to implement how to implement the models and process the input data.

Reviewed on Sep 21, 2024

Could have been more polished like the earlier courses in the deep learning specialization. Particularly the programming exercises could have benefitted from more comments like in earlier courses.

View more reviews