Chevron Left
Вернуться к Introduction to Deep Learning

Отзывы учащихся о курсе Introduction to Deep Learning от партнера НИУ ВШЭ

4.5
звезд
Оценки: 1,806
Рецензии: 421

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:

376–400 из 421 отзывов о курсе Introduction to Deep Learning

автор: Paco J A

1 янв. 2018 г.

Esta muy bien el curso en términos generales, pero para mi gusto falta explicación de algunos temas más en profundidad. Además, los videos de una semana en concreto cuesta seguirlos por el marcado acento hablando inglés

автор: Samson D

16 янв. 2020 г.

The video content is quite good and I've learned a lot. However, the preparation for the exercises is insufficient and the format of fill in the blanks is not really as educative as it is confusing.

автор: Danish S

12 авг. 2020 г.

The title says Introduction to deep learning, whereas in introduction video Prof. Andrei says it is an advance course... I wanted to learn from the basics

автор: Mohamed E A

21 янв. 2018 г.

there is some lecturers are not talking clearly stopping too much while explaining, the materials is very good with high quality

автор: Dizhao J

24 мар. 2018 г.

the pronunciation of the lecturer is not clear and too fast, hope they could speak slower and clearer

автор: Shubhra S

27 мая 2019 г.

The introductory course is good. But I think you should include more reading material for RNN

автор: Kamil M

25 апр. 2018 г.

Neural network introduction is conducted very chaotic. Not all topics are explained well.

автор: Ширнин А А

17 февр. 2021 г.

Не понравилось последнее задание, где нужно людей оценить, потому что работ нет 20 дней

автор: Siwei Y

27 дек. 2017 г.

先不说里面某位小哥嘎嘣儿脆的口音和销魂的语速。只说课程内容本身,首先有些讲义逻辑性太差,某些数学表达式有明显错误, 最后 作业里面的低级错误真的不应该犯。

автор: Mathieu D

15 апр. 2018 г.

not enough content in the video to pass the exam.

автор: Kushagra P

12 апр. 2018 г.

The RNN week was very bad.

автор: 唐志强

29 июля 2018 г.

各种口音的英文发音对母语为非英语的学生很困难

автор: Shahzaib M

19 авг. 2019 г.

theory was good but at the time of Assignment i really felt blank as i have studied nothing, which i mean there is no technical support given in lectures, may be this is my fault that i cannot cop-up to the complexity. but still there is a room for improvement may be 5 to 10 min video to help student understand what they are supposed to do.

starting with coder decoder i literally gave up on assignment. so i had to search web and i felt lack of external matters too from where i could get help i am hoping that this response will the up coming student.

i focused on the things need to be improved but it does not mean that the course was not good over all. starting week was quite good i rate those week 5/5 stars. but later on the journey i had problem in understanding the pronunciation but than i realized its not that it is the material i am not clear of.

Thanks.

автор: Фариман Г

22 авг. 2021 г.

The lectures and lecturers are good. It is very cool that there a lot of contents.

However, there are no pdf materials of lectures and it is inconvenient to search information in video lectures.

Some lectures are a bit of outdated for example there are a lot of lectures about rnn but transformers are not covered. But it is ok. considering that transformers had become popular after this course was created.

The main problem with this course is that almost all assignmens are severly outdated. You should use tensorflow 1 to make them! It is not complicated to work with tf1 but it is very inpractical. The notebooks do not work in colab because it is so outdated. So you should wait 2-6 hours until the model learns weights. It is very frustrating. The quality of the most tasks is not high, too. It is like "take this line, past here".

автор: David P

8 дек. 2019 г.

This is an extremely poorly prepared course in which the lecturers just throw material at you without bothering to make it even slightly comprehensible. One has to struggle really hard to understand what they are talking about -- they often use concepts and terms that have never been defined before, the slides are sloppy and often formulas make no sense. That said, I'll probably continue struggling with the lectures, since this is (unfortunately) the only advanced resource for deep learning at the moment. I really hope the lecturers will listen to the multitude of negative reviews and make an effort to improve their presentation.

автор: HAZEM D

4 июля 2019 г.

good course with great lectures , but the assignments are very painful to complete , they are not hard but the training of the model takes to much time and the coursera notebook always crushes , it took me 1 week to finish an assignment after several trials of training the modal , i ended up by using google Colab with accelerated GPU in order to finish the assignments, also the instructions in the assignments are often not very clear. i suggest to reformulate the assignments and delete or modify the part where you have to train the model and wait several hours to submit the notebook .

автор: Reza S

12 февр. 2021 г.

While trying to be objective, I beleive the only credit this course takes is the extensive syllabus. Otherwise the lectures were terrible and it was almost impossible to follow any subject just by leaning to the course material. At some point I ended up muting the videos and focused on subtitles only. Pedagogically it wasn't design to "teach" so to say, and I practically ended up googling most of the topics so I can graduate this course!

автор: Stefano C

6 янв. 2018 г.

The course has a high potential, with large content and expert instructors. However, you soon realise that the content is indeed too large, and it's never covered with enough details and examples. The most disappointing part, however, is the assignments: the topics covered are too advanced and, as a matter of fact, the learner is only given the chance to implement a tiny part of it.

автор: Sergio A G P

8 июля 2020 г.

I found this course not to be a good introduction to deep learning. It never explained well how to use Tensorflow for even easy things. There was a lot of topics covered, which made the course very shallow. As an introduction, it would have been great to know how to de easy things well, instead of checking lots of topics and not knowing how to fully implement them.

автор: Caio A A O

27 нояб. 2017 г.

It started great, but became a bit too shallow. There's also little to no support from instructors, even when there are bugs.

автор: Tanvi

14 июля 2020 г.

Language problem ,no clear instructions were given for the assignments(Notebook) and no proper reply of Discussion form.

автор: raghuveer n

26 дек. 2017 г.

The accent is very hard to understand and the quality of the recording is not good

автор: Juan S V C

13 июня 2021 г.

Q​uite hard for an Introduction.

автор: Marina Z

7 июля 2020 г.

Worst ever course on Coursera. The lectures are actually well-prepared. The programming homework assignments, however, do not meet the technical requirements of Coursera in terms of dataset volume and the time needed to run the training of the models. It's pain in the bottom to train a model as asked in the course. To transfer the notebooks to Colab to train the models on Google servers is connected to many, many, many hours of additional work to rewrite the scripts. I will not finish this course and I would not suggest to begin with, unless you have nothing to do in this world except to lose your time on the improvement of the assignments.

автор: Fereydoon V

11 нояб. 2017 г.

This low-quality course sucks miserably! I still can't believe that this course has really been approved by Coursera, or perhaps Russians have compromised Coursera too?! Not only the extremely heavy accent of so-called "lecturers" makes it impossible to follow what the hell they're talking about, but also the course construction and the explanations' track lack the bare minimum of pedagogical/instructional design. These folks could have taught this course in Russian, at least it would have been usable for Russian folks!