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: 1,292
Рецензии: 290

## 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

Sep 20, 2019

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

##### AK

Jun 02, 2019

one of the best courses I have attended. clear explanation, clear examples, amazing quizzes & Programming Assignment this course is advanced level, don't enroll it if you are a new starter.

Фильтр по:

## 201–225 из 289 отзывов о курсе Introduction to Deep Learning

автор: Alexey Z

Mar 19, 2020

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

Jan 13, 2020

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

Apr 29, 2019

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: Yaran J

Jan 06, 2019

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

Nov 19, 2017

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

Jul 29, 2019

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

Mar 20, 2018

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: Andrei V

Jun 08, 2018

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: Abhinav U

Dec 02, 2017

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

Jan 08, 2019

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

Mar 18, 2018

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: Sachin

Mar 02, 2019

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

Feb 26, 2018

The course is very good. The last assignment was pretty ambitions with the image captioning but i am glad they did it. Some of the lectures the english is very difficult to follow. Other than that really helpful course.

автор: Tiandong W

Sep 12, 2019

This is an ADVANCED DL course. If you have already learned Andrew Ng's deeplearning.ai course or other basic course, this course is good for you as a test. But if you don't know DL at all, this is not for you.

автор: Hamlet B

Jan 20, 2018

This course is incredibly challenging and the assignments can be frustrating with little guidance, and high bar to pass graders. I give it a high rating because it really pushed me to learn and master details

Dec 17, 2017

I found the content to be interesting and on a good level of advancement, but I also found the exercises to be buggy sometimes or not well thought, which cost a lot of extra time spent on it.

автор: Пронина Д А

Jan 22, 2020

The course was quite useful, but I didn’t really like how the practical tasks were compiled. For some tasks, a lot of time was spent only because of an incorrect description of the task.

автор: Evgeny K

Jun 23, 2018

I didn't like some lectors. However, the course itself was a great start to learn Deep Learning for me. It covered fundamental topics very clearly, so I appreciated this very much.

автор: Georgiy I

May 07, 2018

Great course for recap of crucial things in DL. But, materials seems useless for people, who don't already have an appropriate knowledge about this field of machine learning.

автор: Orazaev A

Feb 02, 2018

Good introductoral material. Most of assignments are done well, but some of them still a bit raw and to solve them students often change code written by course creators.

автор: kareem j

Feb 05, 2020

The content is great, but sometimes some concepts need more illustration. Also, sometimes the language is not spoken perfectly which makes it a bit hard to understand.

автор: Jesper H L

Jul 24, 2019

A good course. But do not think that you can do this course og you are new to AI. IT tales you to the latest, but you midt know the finest and python before you start.

автор: Malay P

Mar 26, 2020

Assignments and Project provided insight into the topic but, sometimes I had to look for some topics from elsewhere as I didn't understand the course videos properly.

автор: Prateek K

Jun 12, 2018

The content and assignments pertaining to MLP, CNN, auto-encoders are great, but I feel it a bit lacking when it came to RNNs and LSTM with the videos/explanation.