Sequence Models

Sequence Models

This course is part of Deep Learning Specialization

Instructors: Andrew Ng

Top Instructor

Skills you'll gain

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

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

Earn a career certificate

Add this credential to your LinkedIn profile, resume, or CV

Share it on social media and in your performance review

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 videosTotal 111 minutes

Why Sequence Models?2 minutesPreview module
Notation8 minutes
Recurrent Neural Network Model16 minutes
Backpropagation Through Time6 minutes
Different Types of RNNs9 minutes
Language Model and Sequence Generation12 minutes
Sampling Novel Sequences8 minutes
Vanishing Gradients with RNNs6 minutes
Gated Recurrent Unit (GRU)16 minutes
Long Short Term Memory (LSTM)9 minutes
Bidirectional RNN8 minutes
Deep RNNs5 minutes

5 readingsTotal 10 minutes

[IMPORTANT] Have questions, issues or ideas? Join our Forum!2 minutes
Clarifications about Upcoming Gated Recurrent Unit (GRU) Video1 minute
Clarifications about Upcoming Long Short Term Memory (LSTM) Video1 minute
Lecture Notes W11 minute
(Optional) Downloading your Notebook, Downloading your Workspace and Refreshing your Workspace5 minutes

1 assignmentTotal 50 minutes

Recurrent Neural Networks 50 minutes

3 programming assignmentsTotal 540 minutes

Building your Recurrent Neural Network - Step by Step180 minutes
Dinosaur Island-Character-Level Language Modeling 180 minutes
Jazz Improvisation with LSTM180 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 videosTotal 98 minutes

Word Representation10 minutesPreview module
Using Word Embeddings9 minutes
Properties of Word Embeddings11 minutes
Embedding Matrix3 minutes
Learning Word Embeddings10 minutes
Word2Vec12 minutes
Negative Sampling11 minutes
GloVe Word Vectors11 minutes
Sentiment Classification7 minutes
Debiasing Word Embeddings11 minutes

2 readingsTotal 2 minutes

Clarifications about Upcoming GloVe Word Vectors Video 1 minute
Lecture Notes W21 minute

1 assignmentTotal 50 minutes

Natural Language Processing & Word Embeddings 50 minutes

2 programming assignmentsTotal 360 minutes

Operations on Word Vectors - Debiasing180 minutes
Emojify180 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 videosTotal 98 minutes

Basic Models6 minutesPreview module
Picking the Most Likely Sentence8 minutes
Beam Search11 minutes
Refinements to Beam Search10 minutes
Error Analysis in Beam Search9 minutes
Bleu Score (Optional)15 minutes
Attention Model Intuition9 minutes
Attention Model12 minutes
Speech Recognition8 minutes
Trigger Word Detection4 minutes

2 readingsTotal 11 minutes

Clarifications about Upcoming Attention Model Video 10 minutes
Lecture Notes W31 minute

1 assignmentTotal 50 minutes

Sequence Models & Attention Mechanism 50 minutes

2 programming assignmentsTotal 360 minutes

Neural Machine Translation180 minutes
Trigger Word Detection180 minutes

What's included

5 videos5 readings1 assignment1 programming assignment3 ungraded labs

5 videosTotal 42 minutes

Transformer Network Intuition5 minutesPreview module
Self-Attention11 minutes
Multi-Head Attention8 minutes
Transformer Network14 minutes
Conclusion and Thank You!2 minutes

5 readingsTotal 33 minutes

Lecture Notes W41 minute
[IMPORTANT] Reminder about end of access to Lab Notebooks2 minutes
References10 minutes
Acknowledgments10 minutes
(Optional) Opportunity to Mentor Other Learners10 minutes

1 assignmentTotal 50 minutes

Transformers 50 minutes

1 programming assignmentTotal 180 minutes

Transformers Architecture with TensorFlow180 minutes

3 ungraded labsTotal 180 minutes

Transformer Pre-processing60 minutes
Transformer Network Application: Named-Entity Recognition60 minutes
Transformer Network Application: Question Answering60 minutes

Instructors

Instructor ratings

4.9 (2,676 ratings)

Top Instructor

Andrew Ng

DeepLearning.AI

48 Courses8,151,918 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

4.8

30,572 reviews

5 stars
83.67%
4 stars
12.96%
3 stars
2.58%
2 stars
0.47%
1 star
0.30%

Showing 3 of 30572

Reviewed on Sep 27, 2018

Great hands on instruction on how RNNs work and how they are used to solve real problems. It was particularly useful to use Conv1D, Bidirectional and Attention layers into RNNs and see how they work.

Reviewed on Feb 18, 2018

Loved the course - it was very interesting. It is also pretty complex, so will probably go through it again to review the concepts and how the models work. Thank you for this wonderful course series!

Reviewed on Mar 13, 2024

Cant express how thankful I am to Andrew Ng, literally thought me from start to finish when my school didnt touch about it, learn a lot and decided to use my knowledge and apply to real world projects

View more reviews