Chevron Left
Voltar para Sequence Models

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

4.8
estrelas
27,127 classificações
3,230 avaliações

Sobre o curso

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....

Melhores avaliações

AM
30 de Jun de 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.

SD
27 de Set de 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.

Filtrar por:

2601 — 2625 de 3,225 Avaliações para o Sequence Models

por Stéphane M

22 de Jun de 2018

The course was good except first week. I did not learn as much as I would like from the programming exercises of week 1. It could be nice to have 4 weeks instead of 3 for this course. Taking more time to cover the week 1 material.

por Shrishti K

26 de Jun de 2020

Everything is perfect, the teaching is excellent, the only problem is the jupyter notebook, its sometimes difficult to debug issues and takes a lot of time and is kind of vague as well in terms of application of the lectures.

por Abid O

1 de Mai de 2018

some topics not explained in detail. Not enough examples to understand some models completely. As an example, I didn't fully understand what are the parameters for the models, their shapes, and how they are used in the model

por Harry L

16 de Jul de 2018

Overall it was pretty informational on introducing NLP to me. However, Keras was a little bit frustrating to learn at the beginning. I found out the forum was a very good resource to learn Keras syntax whenever I was stuck.

por Eric C

12 de Jan de 2020

Great course! I do feel like I'm just scratching the surface of the types of applications that I can make. I think the coding segments still hold our hands a little too much, but you can't beat the clarity of the lectures.

por Nguyen H S

21 de Out de 2018

The course lecture is grade but I hope the assignment is better in guiding structure, something the explanation is hard to follow, and the assignment should include the transfer learning instead of using the trained model.

por Paolo S

8 de Jun de 2019

This was hard to keep up with, maybe too hard. The assignments' difficulty also was on a different level then the lectures maybe there more time should be put into the lecture videos as it was the case for DNN and RNN.

por Aida E

21 de Fev de 2018

The videos and programming exercises were very interesting and insightful. My only complain is some of notebooks for exercises include errors and it was just a time-wasting task to find the "trick" to pass the grader.

por Anshuman M

30 de Jul de 2018

The content is well captured and Andrew really helps build the required intuitions. But, the assignments are too guided. There is no room to struggle for solutions which often proves to be the main source of learning.

por Ryan

15 de Jul de 2021

I​ think the transformer programming exercise of this fifth course is not as good as the others. The methods we must implement are not clearly explained and the research on these really took me a huge amount of time.

por Prateekraj S

28 de Jul de 2020

The exercises are too short and too basic for this course specifically. The task is a great learning experience but there is not much one would struggle with in terms of difficulty as there is too much spoon feeding.

por Ivan

18 de Mar de 2019

Great video lectures, but practical assignments are a pain due to awful auto-grading system and programming expirience in Jupyter in general. Most of the time you'll be searching for an error that isn't really there.

por Fabio R

31 de Out de 2020

Excellent course, excellent lecturer. Unfortunately some of the test data (week3/lab/trigger word detection/XY_dev/* CANNOT BE DOWNLOADED ... The programming lab sections are nice - sometime a bit too helped ... ;)

por Jeffrey D

11 de Mar de 2020

Programming exercises did show you quite a bit, but got complex enough that most of my time was spent reading and understanding the preamble than doing any programming. That being said it delivered on the promise.

por Salamat B

24 de Set de 2018

Course content is really good! However, I found it quite difficult to truly understand deep learning algorithms. However, it provides good glimpse of of sequence models and intuitions behind various useful models.

por Georges B

20 de Fev de 2018

Great course and material, Andrew NG really know who to explain difficult subjects in an intuitive way. However, the course seems that it still needs some work (there are some bugs in the lectures and assignments)

por Mayank A

30 de Jun de 2020

The NLP Section of this course is quite difficult to understand(The Notations are quite confusing as well as prior knowledge is required to understand) but other than that RNN, GRU, LTSM are explained clearly.

por Seungjin B

8 de Set de 2018

Week1 lessons are a little complex than the previous classes and there are gaps between ground-up python version and keras version of LSTM model. Keras will need to be taught a bit more in detail to follow up.

por Lester A S D C

29 de Jul de 2019

This is by far the hardest course in the specialization. But it was explained well. My only complain is there were errors in the first programming exercise. All in all, I learned a lot in this specialization.

por Guoqin M

2 de Jul de 2018

Great content! I really love Andrew's teaching style. (1 star deduction for some programming assignments where I spent time debugging but it turned out that the point deduction was due to the grading system.)

por Divya G

25 de Mar de 2019

The programming exercises are a little heavy in this course where we need to load and re-load for them to give correct output even if the code had been correct all throughout. Otherwise, the course is great.

por Mathieu D

10 de Set de 2018

4 stars and not 5 stars because the course is shorter than the others and it feels like an exemple in classical forecasting is lacking (sales, time series...).

Really interesting but may be too focus on NLP.

por Zhaoqing X

24 de Jul de 2018

It's an excellent course! I will give it 5 stars if it could offer more interesting and meaningful assignments(Not offend, but it a little too easy and the assignments are not very related to the real work).

por Ayush N G

23 de Set de 2019

The course should contain more explanation about natural language processing like tf-idf,lemmatization,stemming,dialog flow. Although i got a good explanation of working of RNNs,LSTM and machine translation

por Md Z S

3 de Fev de 2019

Great course to start off with sequence model. The programming exercises were in depth and deliver a great learning experience. Would love to see more of sequence literature in the course's future versions.