Chevron Left
Вернуться к Introduction to Deep Learning

Отзывы учащихся о курсе Introduction to Deep Learning от партнера Национальный исследовательский университет "Высшая школа экономики"

4.6
звезд
Оценки: 1,691
Рецензии: 394

О курсе

The goal of this course is to give learners basic understanding of modern neural networks and their applications in computer vision and natural language understanding. The course starts with a recap of linear models and discussion of stochastic optimization methods that are crucial for training deep neural networks. Learners will study all popular building blocks of neural networks including fully connected layers, convolutional and recurrent layers. Learners will use these building blocks to define complex modern architectures in TensorFlow and Keras frameworks. In the course project learner will implement deep neural network for the task of image captioning which solves the problem of giving a text description for an input image. The prerequisites for this course are: 1) Basic knowledge of Python. 2) Basic linear algebra and probability. Please note that this is an advanced course and we assume basic knowledge of machine learning. You should understand: 1) Linear regression: mean squared error, analytical solution. 2) Logistic regression: model, cross-entropy loss, class probability estimation. 3) Gradient descent for linear models. Derivatives of MSE and cross-entropy loss functions. 4) The problem of overfitting. 5) Regularization for linear models. Do you have technical problems? Write to us: coursera@hse.ru...

Лучшие рецензии

DK
19 сент. 2019 г.

one of the excellent courses in deep learning. As stated its advanced and enjoyed a lot in solving the assignments. looking forward for more such courses especially in Natural language processing

TP
8 авг. 2020 г.

A very good course and it is truly insightful. This course deals with more on the concepts therefore I have a better understanding of what is really happening when I build deep learning models.

Фильтр по:

251–275 из 392 отзывов о курсе Introduction to Deep Learning

автор: Anselmo F

22 мар. 2020 г.

Very interesting course, the notebooks are very useful and all the concepts are very well motivated and explained. I just found some bugs in the course and had some problems with the explanations of week 4 and I believe week 5 lacked the explanation of some basic concepts, but all of these gaps could be filled with a research of additional material. Anyway, I recommend this even for beginners, all you need to know are derivatives and some Python basics.

автор: Abhinav S

22 апр. 2018 г.

It is not an easy course, but the course projects are very nice. I really liked the RNN and CNN parts of this course very well explained and had some rigour to it.

My only complaint about the course is that it is not self contained. You will have to read up a lot more and refer to other sources on the internet to get a firm grasp of what is being taught and then go ahead to tackle the exercises.

автор: Jay U

26 июня 2018 г.

+ Instructors go into considerable theoretical depth and are very knowledgeable. + Great assignments, but can be pretty challenging+ You will learning a lot by taking this course.-Some instructors are much better than others- Instructors rely too much on slide reading. Lectures lack interactivity other than an occasional pop question.- Discussion groups are not active. Many posts go unanswered

автор: Zhen Y

31 янв. 2018 г.

I found the first assignment (Week2) very difficult if you didn't have enough experience in Tensorflow to start with. Later on, the assignments became more enjoyable.

The course is more advanced than Machine Learning and DeepLearning.AI. Lots of concepts are gone through very quickly. It is not ideal if you are new to the subject. However, it covers great details in a short course.

автор: Saptashwa B

20 янв. 2020 г.

Very nice course with a great project in the end. I just think this course is little too big (7 weeks) and still at times fail to cover important points in detail. I assume they are covered in the next courses of the specialization. Specially convolutional neural network for image classification requires better explanations at some part. Just my opinion though !

автор: Juho H

25 июня 2020 г.

Very challenging assignments, and unfortunately using the old version of Tensorflow. On the other hand, you really get an understanding on many things other courses skip (like the different optimizer algorithms), and the labs are very interesting. But you really need to have already fairly much experience in machine learning before tackling this one!

автор: Ipsita S

17 февр. 2020 г.

As I'm familiar with deep learning I took a advanced course in order to learn new things and enhance what I already know. I have given a four star because I didn't find things new for me but I continued because the course is well structured and the assignments actually were helpful for practical learning.

Overall a good experience for me!

автор: Emanuel P F

9 янв. 2019 г.

It is not a introductory course! The course provides an excellent path showing the most tools in deep learning techniques but you have to spend more time looking for additional material to supplementary this course. In general you will learn the basic about Neural Networks, Convolutional Neural Networks, and Natural Language Processing.

автор: Alexey Z

19 мар. 2020 г.

Autoencoders, RNN: Theory ovekill, which seems to be pretty useless, as after listening and trying to follow the lectures logic, you need to go outside to read explanations. E.g., after lectures I had 0 understanding of how LSTM is implemented, how it really works, even how actually it helps avoding gradient expls/vanishing.

автор: Γεώργιος Κ

13 янв. 2020 г.

This was absolutely an interesting and enlightening course. There are things left unexplained and appear from nowhere in the programming assignment like RMSprop. Though the assignments can be passed even with these dark spots I think this is a reason that this is not a five-star course. In fact, I would rate it as 4.5 stars.

автор: Driaan J

29 апр. 2019 г.

The content of the course is really excellent, and the lecturers' knowledge is just superb.

The only drawback of the course is that the lecturers' native language is not English, and accordingly it is sometimes difficult to understand them. But there are subtext to the lectures in English that one can refer to.

автор: GOUTAM K

28 мая 2020 г.

Lectures were short and to understand the topic, we need to browse those topics online. Programming assignments were tough and interesting but mostly pre-coded. But still the code quality was good and reading the code was interesting. Overall a good course but not much recommendable for a beginner.

автор: Yaran J

6 янв. 2019 г.

Good overview of deep learning topics like CNN and RNN, and also hands on coding assignment of Tensorflow. However, this is a big gap between the video material and the programming assignment. Need to add more training for Tensorflow before deep learning models. And the instructors speak too fast.

автор: Max P Z

19 нояб. 2017 г.

The content of the course and programming assignments is well designed. However, there're some technical issues with the assignments (eg. unable to submit the results for honor content). And some requirements for the accuracy/loss in the programming assignments are really too high.

автор: Margarita C

29 июля 2019 г.

My impression of the course is controversial, like it itself is: an introduction to advanced DL. Tough and frustrating for the first experience in DL. The course was useful, but, as everyone notes, in the end you learn from materials you find in the Internet to complete the tasks.

автор: Tue R L C

20 мар. 2018 г.

This is a relative new courses which shows in some of the assignments e.g. minor mistakes and weird hacks required to pass them. The final project is a bit of a let down as it basically requires the user to do some data processing in python but no "real" machine learning.

автор: Javier C D

1 янв. 2021 г.

Very interesting course if you have some previous knowledge of Machine Learning. Lectures are interesting and the exercises are very insightful and very well designed. The only bad aspect is that the exercises use the old tensorflow 1 instead of the current tensorflow 2.

автор: Gonzalo C

20 июня 2020 г.

You should record again all the videos of week 4, because the pronunciation in that videos are not good enough to understand well all the details, and It's kind annoying to listen all the videos, and keep listening for long time. The rest was a great course

автор: Andrei V

8 июня 2018 г.

Nice intro to DL. Final assignement is quite hard to accomplish, as you don't know the goal - loss should not too small, not too big (but are the boundaries?). For me it was ok, as I'm running on GPUs, but it should be painfull path for CPU folks.

автор: Thomas L

29 авг. 2020 г.

The course is greatly taught and benefits from having several teachers, each having their own touch and approach to the material.

An upgrade of the programming assignments to the latest version of tensorflow would however be more than welcome!

автор: Abhinav U

2 дек. 2017 г.

It's a good course for people with some prior experience and background in machine learning (specially neural networks). The exercises and projects were a bit difficult and needed effort to get correct but helped reinforce the concepts.

автор: Milos V

8 янв. 2019 г.

Interesting and useful course. Capstone project was quite difficult, but I learned a lot - so I do not want to complain about it. Maybe a bit more code-related things during the lectures would be useful to make capstone project easier.

автор: nicole s

18 мар. 2018 г.

Very good content and teachers. Indeed advanced level, for the less advanced it would have been helpful to include some more clarifications towards solving the assignments and the mathematical derivation of the main concepts.

автор: Georgios P (

26 апр. 2020 г.

It is a good course overall, but some subjects feel a bit rushes. Also, it would be much better if authors were adding a week for learning the tools that are used in program assignments (Tensorflow and Keras specifically).

автор: Sachin

1 мар. 2019 г.

really nice course to hone your skills. but sometimes the assignments are really really tough and no hint is provided how to solve them. i was having problem because of my weak python skills. afterall course is relly nice