Chevron Left
Вернуться к Introduction to Deep Learning

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

Оценки: 1,830
Рецензии: 428

О курсе

The goal of this online 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:

Лучшие рецензии

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

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 426 отзывов о курсе Introduction to Deep Learning

автор: Aleksandr G

20 авг. 2019 г.

Very advanced!

автор: Akshit V

13 июля 2019 г.

Great Course!

автор: edward j

28 февр. 2018 г.

Great course!

автор: Ajayi E A

4 июля 2020 г.


автор: Alfonso M

31 янв. 2019 г.

Good course.

автор: Krishna H

10 июня 2020 г.


автор: Alex

1 мар. 2018 г.

Nice work.

автор: Xiao M

18 дек. 2017 г.

Very gooda

автор: Vital P R

23 авг. 2021 г.

very good

автор: Dr.S.Karthick

10 февр. 2021 г.


автор: Sbabti M z

27 окт. 2020 г.


автор: Kollipaka s

22 мая 2020 г.

very good

автор: M A B

25 февр. 2019 г.


автор: 胡哲维

23 дек. 2018 г.


автор: Franco P

29 сент. 2019 г.


автор: Parag H S

13 авг. 2019 г.



16 июля 2020 г.


автор: Имангулов А Б

16 июля 2019 г.


автор: heechan s

10 сент. 2019 г.


автор: Sasikumar G

19 июля 2018 г.


автор: Колодин Е И

18 авг. 2019 г.


автор: Arsenie a

5 апр. 2018 г.


автор: Aparna S

6 янв. 2020 г.

The material that it is trying to cover is very good. The programming assignments are intuitive with fill in the blanks kind of approach. Finishing them and the quizzes was a breeze.

But if you are new to tensorflow and Keras and a picky like me in wanting to know exactly what is going on and how, this course is wanting details.

It does have few other minor hitches -

-It has missing links to resources (you can dig them out though)

-mistakes in slides (that they embarrassingly correct inside)

-If you care about math, it might be disappointing when you see formulae with ill-defined variables and assumptions about notations that are not discussed. If you have a background, and do simple web search you will find it out in no time though.


автор: Bikhyat A

26 июля 2020 г.

The course is really awesome, especially the lecturer Andrei Zimovnonv's lectures are really good. His flow, the concepts he provide, all are lucid. However, Alexander Panin's lectures are, I think quit difficult to understand. Most of the times, he suddenly delivers so fast that you can't even hear what he actually said. I think, he should work on that. And honestly, I still have lot's of confusion in the portions he covered i.e. embedding, auto-encoders, adversial networks etc. One more thing what I'd like to add is, the instructions provided in the assignment notebooks are sometime very hard to understand making me feel they're confusing and incomplete.

автор: Arend Z

9 февр. 2018 г.

Very helpful to get a good basic understanding of the different types of neural networks and their application. After finishing the course, I do not yet feel confident enough to build my own neural network applications. Maybe this can be solved by having more programming assignments at 'beginner' level, before 'stepping up' the complexity.

The provided 'example' codes - that work after successful completion - serve as a good starting point to build your own neural networks.