Save for later

Sequence Models

Deep Learning,

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.

Get Details and Enroll Now

OpenCourser is an affiliate partner of Coursera and may earn a commission when you buy through our links.

Get a Reminder

Send to:
Rating 4.6 based on 2,077 ratings
Length 5 weeks
Effort At the rate of 5 hours a week, it typically takes 5 weeks to complete this course
Starts Jun 26 (23 weeks ago)
Cost $69
From via Coursera
Instructors Andrew Ng, Head Teaching Assistant - Kian Katanforoosh, Teaching Assistant - Younes Bensouda Mourri, Kian Katanforoosh, Younes Bensouda Mourri
Download Videos On all desktop and mobile devices
Language English
Subjects Programming Data Science
Tags Computer Science Data Science Algorithms Machine Learning

Get a Reminder

Send to:

Similar Courses

What people are saying

neural network

this course provide an adequate and what you want to know about recurrent neural network but it does require lots of programming skills to accomplish this course.

This course feels rushed and he doesn't take the time to clarify confusing issues - for example, when he first introduces how to learn word embeddings he calls the neural network you use a "language model" even though the network bears no resemblance to the language model we learned in week 1.

His ability to break down a complicated concept like neural networks and deep learning so that a non-math, non computer person like me actually understands the underlying mechanisms is quite extraordinary.

Very good introduction to RNN, GRU and LTSM neural networks with good practical examples.

Simply fantastic :D The course is well-structured, and a nice introduction to sequence-related neural networks.

Outstanding Very well laid out with good coverage and good insights about what types/sizes of neural networks are prevalent in commercial systems.

Pretty good, for learning recurrent neural network and neural machine translation, and I learned a lot about Keras in the program assignments.

Homework is also very helpful to understand what is going on step by step under Recurrent Neural Network.

This course has helped me understand the basics of Recurrent Neural Network.

We learn Recurrent Neural Network (RNN) /Sequence Model, which allow translation or trigger word (like "Hey Siri!").

These lectures are good for intuition and background of different types of Neural Network architectures.

This is an amazing course, it Provides a great Help...i have learned lots n lots of stuff about NLP, Learn about recurrent neural networks that work extremely well on temporal data, word vector representations and embedding layers --that are explained in a concise manner, and more importantly I love the Attention mechanism, the model that understand where it should focus...... its attention given a sequence of inputs.... amazing amazing ..highly Recommended.... Thankyou Good Thx Andrew et al.

gets your foot into the door of recurrent neural networks!

This specialization helped me overall to gain a solid fundamentals and strong intuition about building blocks of Neural Networks.

Read more

speech recognition

I feel I have a better understanding of how some of the "magic" technology like virtual assistants and speech recognition work.

Excellent course to learn about speech recognition and translation!

Great design of the structure to cover both language modeling and speech recognition.

Very Useful course Gives the student an excellent perspective on how to go about word embeddings & speech recognition.

And I have learned many intuitions and skills of Sequence Models and its application in various NLP tasks and speech recognition.

May be extend this to 4 to 5 weeks and spend little more time on speech recognition, music generation and other audio data processing would have helped.Unlike all other earlier modules, this one had many issues with grader and many errors in note book templates.

NLP and speech recognition intition with real world coding examples.

A very good intro to NLP/Speech Recognition with Deep Learning (RNN) This is the best course I've learnt.

It is better to provide more contents on Speech Recognition.

This Course was a nice introduction to Sequence-To-Sequence Models, where we learned about applications involving speech recognition, machine translation, & captioning of images or videos.

Smooth and hands-on walkthrough of basics of NLP and speech recognition.

It is a very complete course I learned a lot about various network architectures to use in language model, speech recognition, music generation, etc.

Best specializatin course I have found and the insights given in this course are truely wonderfull A great introduction to Recurrent Neural Network models with lots of examples (text generation, music generation, sentiment analysis, word embedding, speech recognition, attention-based machine translations etc.).

very good Amazing project on detecting words in speech recognition excellent!

Read more

deep learning specialization

thank u for helping me understanding RNN/LSTM finally The Sequence Models course was the one I sought out in the deep learning specialization.

really useful Worthwhile conclusion to the deep learning specialization.

"Machine Learning" by Andrew Ng is my 2nd Coursera course in 2013, and "Sequence Models - Deep Learning Specialization" is my latest Coursera course in 2018.

Great course and teaching as usual Thanks Professor Andrew Ng and team for the deep learning specialization.

This course, being relatively new, was less polished compared to the other courses in Deep Learning Specialization.

The practical exercises are interesting but I found them in a bit raw state compared to the previous courses of the Deep Learning Specialization.

The best course in the Deep Learning Specialization.

The instructions were really unclear, it could have been better Thank you so much for the entire deep learning specialization.

Muchas Gracias... !The course is very good, particularly I am very grateful to COURSERA, for giving me the opportunity to do the five courses of the Deep Learning Specialization with financial aid and allowing me to have access to this type of training and certification.

As with all the 5 courses in the Deep Learning Specialization, the video lectures were amazing, thoughtfully designed (and separated) and gave an understandable overview of the content.

I think It would be better If there was a capstone project for the final course of deep learning specialization.

This is Course 5 of the Deep Learning Specialization, and the last one.

Wonderful end to this Deep Learning Specialization.

Amazing course Great ending to the Deep Learning Specialization.

Read more

recurrent neural networks

a very good course with lots practical assignments which helps me in developing AI with Recurrent Neural Networks and apply word2vecs model.

I believe it is useful to take this course in order and it makes sense to study it as a part of the series, though technically that is not necessary.This is one of the best courses to take if you want to understand the basics of Sequence Models (Recurrent Neural Networks).

I realize though that deep learning requires a lot of practice and experimentation and completing this course (and specialization) is just a tiny first step .. Learnt many useful techniques and knowledge of Sequence Models and Recurrent Neural Networks.

Very pleasant introduction to the field of recurrent neural networks!

Likely due to the rush of getting this final course out Best course you can find about recurrent neural networks.

I learned many new things about practical applications of recurrent neural networks in this class and found the natural language emphasis to be very useful, particularly for certain problems I have been working on for some time!

Professor Ng's lectures provided intuitive ways to understand the complex recurrent neural networks and how to apply it in real world applications.

The course is very interesting and it gives an insight into recurrent neural networks (RNN).

I got to learn a lot very efficiently about Recurrent Neural Networks!!!

This Is very helpful course in order to learn Recurrent Neural Networks.

With this course it's possible to conclude that recurrent neural networks are the most powerful variant of neural networks.

In this last module of the specialization, you will learn in details how the recurrent neural networks works.

Again, nice videos and explanations, and well-designed useful programming assignment (TensorFlow/Keras and numpy) The best online course I've seen anywhere about recurrent neural networks!

Really enjoyed the insightful content of this course Nice intro in recurrent neural networks.I'd prefer more focus on why the architectures are designed the way they are.

Read more

natural language processing

Assignments are very helpful 非常好! course, but i think it should more details Nice mix of simple and complext concept plus good exposure to Keras A very good course which helps of understand basics of sequence modelling and its various applications in Natural Language Processing.

RNN is a technically-difficult-to-understand, still-evolving field of Neural Networks, and it has thus far found remarkable uses in a wide variety of field, ranging from Natural Language Processing (NLP) to Voice-to-Text conversion and Music Synthsis, to name a few.

Very nice course if you want to apply natural language processing start through python.Very nice course to start your crazy projects in NLP.

I highly recommend this course to anyone interested in natural language processing or speech recognition.

Excellent course regarding Recurrent Neural Networks and Natural Language processing.

Thank you Andrew This course is perfect to learn deep insights of natural language processing, word2vec, speech recognition, trigger word detection and sentiment analysis among others.

Very usefull and structured tutorial The course should contain more explanation about natural language processing like tf-idf,lemmatization,stemming,dialog flow.

But I learned some basic knowledge about Natural Language Processing and Speech Recognition through this course.

Before starting the course, I wanted to have a strong knowledge of the basics of Natural Language Processing as I wanted to specialize in this domain.

This course teaches in-depth knowledge of sequence models in natural language processing and speech regocnition .

Very effective at improving my understanding of RNNs (and its variants), Natural Language Processing, and some basics regarding working with audio data.

Amazing Course to learn RNN and Natural Language Processing.

Another outstanding course about Deep Learning.It teaches Recurrent Neural Networks from the basics up to industry applications such as Speech Recognition and Natural Language Processing.

A great course for everyone who wants to use deep learning for natural language processing.

Read more

word embedding

I've got chance to learn some popular and powerful methods within the years, like word embedding and attention mechanism.

this course is the most difficult in deep learning specification, but i think Andrew NG should design more homework for word embeddings and bidirectional rnn, i do not understand how it works yet Great lectures, great teacher!I would have given 5 stars but for the problems in the exercises / grader.

Would highly recommend this to anyone willing to learn NLP, Sequence Modelling, Word Embeddings, Machine Translation and related stuff.

Loved the Sequence model chapters especially with word embeddings, sentiment classification and Speech recognition exercises Excellent course Great course on Sequence Models by Andrew Ng.

Also I hope the Word2Vec algorithm and word embedding in general is explained better and with exact steps.

I was a bit disappointed about NLP section as it brushed over word embedding and left me without much understanding on how they are estimated.

Word embeddings cleared up a lot, but the entire course was a lot of information to digest at once.

Really good choice of topics, including state of the art tools like attention and word embeddings.

This course offers a great introduction to the models: RNN, GRU and LSTM.In addition, it illustrates the power of "Word Embedding" and "Attention Model".

This course is great to get intuitive understanding of Word Embeddings, RNNs, LSTMs, GRUs and Attention Models.You will have great explainer videos and some excellent programming exercises.

What impresses me most is the lesson of "Debiasing word embeddings", it shows that AI could be designed to do more against human stale thoughts, which sets up a good principle for designing AI.

You can tell there is a lot of work behind it.THANKS Assignments are not up t the mark.. Expected to have high vocabulary size word embedding assignment, Machine Translation assignments Overall it was pretty informational on introducing NLP to me.

Read more

trigger word detection

You get to practice, (1) Music synthesis, (2) NLP and Sentiment Analysis, (3) Trigger Word Detection (Hello Google, Hey Siri, Alexa!

I still have some doubts on how to use them correctly (for example the use of time distributed layer in the last exercise 'trigger word detection' that we didn't use in the architecture for the exercise about attention mechanism) An extremely well thought off and comprehensive introduction to sequence models, with examples taken from the most important/interesting application domains.

At the end you'd learn so much that by just looking at a single slide of an overview of Trigger Word Detection you could make the entire DL model yourself.

I really enjoyed and had fun with the programing assignments specially the Emojify and the trigger word detection.

The programming assignment on trigger word detection gives an insight into the practical machine learning implementation for speech recognition.

I liked the "Trigger word detection" (the last assignment of this course) very much.

Un véritable apprentissage et un plaisir surtout sur le Trigger Word Detection qui était très intéressant.Totally more difficult than anything before.

It was a pleasure, especially for the Trigger Word Detection which was very interesting.

Everything is great except the last assignment - trigger word detection is hard to save and submit, and i can't even open it sometime.

Especially the trigger word detection algorithm worked perfect with my own voice, that was satisfying of course.

Week 3: quite a complected network was used for trigger word detection; however, it is not clear why exactly this architecture was used; specific order of dropout, batchnorm and GRU seems to be a pure magic; at least, a few words why this combination is picked are needed.

Read more

highly recommended

Great effort by Prof. Andrew NG, highly recommended.

overal impression : exceptional and highly recommended.

Highly recommended to all who what to learn the "deep" in Deep Learning!

Highly recommended.

Again overall - highly recommended The lecture for Sequence model was good motivation to get interesting about text and audio processing.

I really thank you for providing the amazing course highly recommended for everyone, it is difficult at the beginning but at hte end of the course will be understood It' a excelent course.

Highly recommended Very Useful Highly recommended course to understand the concept of speech recognition models, very real use cases.

Highly recommended!

Highly recommended course I learned a lot, thank you very much!

This is highly recommended for the deep learning and machine learning enthusiasts.

Read more

looking forward

This was the course in the series that was most relevant to my topic of interest, so I was looking forward to it and enjoyed every moment of it.

I was looking forward to learn more in-depth about this model, but I didn't feel I get all that I wanted.

I am looking forward to more courses/specialization from DeepLearning.AI team in the coming months :) Some programming assignments have few errors in them (wrong equations, wrong expected output etc.)

Looking forward to any course Andrew Ng might teach in the future.

I'm looking forward to have a next level course on top of this track.

Great course content and well explained by Andrew, looking forward to apply the learning to solve real world problems.

Kinda sad that this journey is over but looking forward to applying all that I have learnt.

I have gained so much confidence after completing these set of 5 courses and looking forward to build some cool projects on my own using the concepts that i have learned in past 5 months.

Looking forward to new courses - maybe Reinforcement Learning, GANs?

Read more

familiar with keras

Spend some time on homework since I'm not very familiar with keras.

For practical assignments I recommend getting familiar with Keras syntax and workflow, as here there is little hand-holding here,.

Overall, I do highly recommend this course, but be forewarned about the need to be familiar with Keras before starting.

However, I'm not very familiar with Keras and working on the Keras code really takes my time even I'm quite experienced with Tensorflow.

Read more

trying to figure

The programming exercises should be revamped to focus more on understanding what is happening in the program rather than trying to figure out Keras syntax (which is also useful, but perhaps better suited for a prep course).

I spent almost all my time trying to figure out Keras syntax, without ever having a Keras tutorial or anything.

Before this course, I spent many hours reading papers on LSTMs and trying to figure out what is going on with all these "Gates", but couldn't understand intuitions behind them.

It is particularly frustrating for those trying to work on the optional/ungraded programming assignment sections that have some incorrect comparison values, as much time will be wasted trying to figure out the source of the error.

Read more

first 3 courses

The main thing i like about first 3 courses, they were really deep.

I took this course after a long pause after I finished the first 3 courses.

I feel that first 3 courses were much better prepared; though CNNs/RNNs are still super-useful despite not being 100% polished.

While the first 3 courses raise your knowledge of ANN in preparation to the 4th one, it is a little more difficult to understand this 5th course.

Read more


An overview of related careers and their average salaries in the US. Bars indicate income percentile.

Learning Services $59k

Computer Vision, Deep Learning Engineer $67k

Computer Vision & Deep Learning Engineer $67k

Deep Clean Sales Specialist $76k

Deep clean specialist $76k

Deep Learning Research Scientist $86k

Deep Learning Research Engineer $88k

Research Scientist - Deep Learning $91k

Senior Learning Specialist, Learning and Development $102k

Deep Learning R&D Engineer $127k

Learning Assitant $142k

Deep Submergence Systems Program Manager $157k

Write a review

Your opinion matters. Tell us what you think.

Rating 4.6 based on 2,077 ratings
Length 5 weeks
Effort At the rate of 5 hours a week, it typically takes 5 weeks to complete this course
Starts Jun 26 (23 weeks ago)
Cost $69
From via Coursera
Instructors Andrew Ng, Head Teaching Assistant - Kian Katanforoosh, Teaching Assistant - Younes Bensouda Mourri, Kian Katanforoosh, Younes Bensouda Mourri
Download Videos On all desktop and mobile devices
Language English
Subjects Programming Data Science
Tags Computer Science Data Science Algorithms Machine Learning

Similar Courses

Sorted by relevance

Like this course?

Here's what to do next:

  • Save this course for later
  • Get more details from the course provider
  • Enroll in this course
Enroll Now