Chevron Left
Voltar para Sequence Models

Comentários e feedback de alunos de Sequence Models da instituição deeplearning.ai

4.8
15,930 classificações
1,745 avaliações

Sobre o curso

This course will teach you how to build models for natural language, audio, and other sequence data. Thanks to deep learning, sequence algorithms are working far better than just two years ago, and this is enabling numerous exciting applications in speech recognition, music synthesis, chatbots, machine translation, natural language understanding, and many others. You will: - Understand how to build and train Recurrent Neural Networks (RNNs), and commonly-used variants such as GRUs and LSTMs. - Be able to apply sequence models to natural language problems, including text synthesis. - Be able to apply sequence models to audio applications, including speech recognition and music synthesis. This is the fifth and final course of the Deep Learning Specialization. deeplearning.ai is also partnering with the NVIDIA Deep Learning Institute (DLI) in Course 5, Sequence Models, to provide a programming assignment on Machine Translation with deep learning. You will have the opportunity to build a deep learning project with cutting-edge, industry-relevant content....

Melhores avaliações

JY

Oct 30, 2018

The lectures covers lots of SOTA deep learning algorithms and the lectures are well-designed and easy to understand. The programming assignment is really good to enhance the understanding of lectures.

AM

Jul 01, 2019

The course is very good and has taught me the all the important concepts required to build a sequence model. The assignments are also very neatly and precisely designed for the real world application.

Filtrar por:

1651 — 1675 de {totalReviews} Avaliações para o Sequence Models

por Michael K

Aug 06, 2018

Assignments are very buggy and instructions misleading or incomplete. However the core material is excellent

por Xueying L

Jul 22, 2018

Too narrow focusing on applications in NLP

por André T D S

Oct 02, 2018

Bugs in the programming assignments grading kills the flow

por Hang Y

Aug 24, 2018

Compared with previous courses, this one seems to be rushed. The focus on applications seems to be much higher than the theoretic side.

por Arjan G

Mar 03, 2018

Nice to learn how RNN's work. But too rough around the edges for a 5-star score.

Good points:

I learned RNNs, language models and many other useful techniques

Subject matter is mostly well explained in the lectures

Original authors of a technique are cited

Bad points:

Some things should be explained more elaborately while other explanations can be shorter, especially in the assignments.

Mistakes in the editing in the audio clips of the lectures

Mistakes in the notebooks, sometimes non-intuitive/bad coding principles are used

por Devin F

Mar 11, 2018

For me, there was a large gap on time between when course 4 and 5 were offered (months). This unfortunately was enough for me to forget everything I learned about Keras.

Of course, this course assumes you know Keras so I was behind for the labs

Material is interesting though.

por Suresh D

Mar 26, 2018

I guess as the subject matter becomes more complex, more training is required on the underlying frameworks being used- Keras, TensorFlow etc. Did not feel that sufficient time was spent on understanding the underlying frameworks. Also the TA work is of spotty quality. But I love the way Andrew teaches.

por Parikshit D

May 27, 2018

The assignments are not very satisfactory..

por Yash R S

May 09, 2018

Not as great as the other courses in the specialisation. The assignments can be a little off putting, but lectures are top class again.

por Thomas N

Mar 09, 2018

Good subject, but a lot of the course material (like lecture slides and problem sets) was either unavailable or out of date.

por Benoit D F

Mar 19, 2018

Very interesting topic but coding exercices and quizzes were a bit clunky and in need for ironing

por Ramon R

May 08, 2018

Unlike the other courses which Andrew Ng provides, this one contains many spelling mistakes in the programming assignment, the programming assignments are less structured and understandable (missing or wrong information in nearly every assignment) and an introduction to keras is missing. I found it great that the keras framework is an important component of this course, but unlike the tensorflow introduction it is missing here. It is frustrating, when you might have the right functions but no information how to input and determine the correct variables for the functions. Anyway I found the outline of the course very good as it gives a good overview of many methods and how they work. To my mind the consistency of the assignments and also the story telling needs to be improved to reach the level of other courses where Andrew is involved. It appeared more chaotic and the complexity of the algorithms is overwhelming, so a better introduction to how they work, might be appealing. In the end, I worked through it and I gained a basic understanding of keras and RNN algorithms. So it was definitely worth it.

por Pablo M

Mar 18, 2018

Despite being a great introduction to many NLP concepts, the programming exercises are a bit too much "fill-in-the-blanks" and not challenging enough. It is still a great course !

por 田奇

Mar 03, 2018

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

por Sumandeep B

Mar 30, 2018

This course is good for introduction to sequence networks, but I felt this is not at par with the previous course 4 (CNN). This feels a bit hurriedly done, with many important things only just touched upon. This should have been a 4 week course like the previous module. Then due attention could have been given to the field of speech, audio, sequence domain.

por Javed S

Mar 29, 2018

Good but i expected more. The main thing i like about first 3 courses, they were really deep. In the last two courses we have skipped the backpropogation. Now this is something which you can keep optional. I like the way Andrew Ng teaches, going to the basics, and that is why I came here and paid 40 euros per month. Also, there are few stuff missing like Generative models, Adversarial networks, GAN and etc. It would be good if Andrew can have more courses related to this and deep (as it is deep learning :))

por Slobodan C

Feb 20, 2018

The best part of the course are "intuitions" presented by Prof. Ng. The worst parts are technical problems with Coursera infrastructure, and insufficient number of mentors available to offer suggestions. For example, in forums there are some doubts about the optional parts of assignments (bad formulas etc.), but these quite valid questions are just not addressed by anybody. I would also suggest adding a separate course on Keras as a part of the specialization, because the Keras introduction offered in a specialization is way too basic. This makes it quite difficult to go through the assignments for the sequential models. It would also be helpful to extend the last two courses to five weeks or so, to cover course material in more details.

por Pankaj R

May 08, 2018

Require a little depth, considering the complexibility. At least 4 Week course should be their instead of 3

por 许晶鑫

Jun 11, 2018

The supports in keras programming was so poor, that I could not quite understand each step. And the server was horrible, always got 405 response when saving my codes.

por Aliaksandr P

Mar 31, 2018

This is a very interesting topic. However, I believe the course itself can be improved. I believe there can be more information about NLP and sequence models in lectures. It would be nice to add lectures with practical suggestions about training and tuning sequence models. There were lots of typos and mistakes in notebooks that were found by other fellow students and not addressed by mentors.

por Shanger L

Jun 05, 2018

does HW created/reviewed by different ones?

por Zhao H

Jul 06, 2018

Too much was given in external python code for the first week's assignment (that should be learnt by us): not a good thing for us to gain a good understanding

por Fernando A G

Jul 27, 2018

I enjoyed all the courses, from my personal point of view this course was not that fun as the other courses. Except for the trigger assignment it was awesome!

por CARLOS G G

Jul 26, 2018

good

por Luca B

Jul 27, 2018

A nice course after all, but I expected something more. It is valuable if you know nothing about RNN and NLP, or if you know something and want to go a little deeper and work on some guided keras examples.

What it is not, is an in depth RNN course. It's very short: in my case the 3 weeks boiled down to 2.5 fulltime days. Not enough for a full review of the topic.

Homeworks are interesting but:

-very simple, no large scale application

-small dataset

-short rounds of CPU training: no GPU, no access to server clusters

-keras layers are used without much explanation about it, this is sad since keras docs is really incomplete about usage examples. I'm referring to calling an LSTM layer inside a loop to manually create all the timestep stucture!

-keras layers are used that have never been introduced in the course (such as BatchNormalization)

-often heuristics for network topology and hyperparameter values are not clearly explained, leaving the student with no insights on how to approach different tasks