Вернуться к Introduction to Deep Learning

4.6

звезд

Оценки: 1,413

•

Рецензии: 323

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...

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

May 29, 2020

The hardest, yet most satisfying course I've ever taken in deep learning, by the end of the course I was doing stuff that was borderline sci-fi and that was just "introduction" to deep learning

Фильтр по:

автор: Федоров Ф

•Nov 18, 2018

i think that the explanations and examples in the notebooks was not always sufficient

автор: Igor B

•Feb 08, 2019

The course indeed gives an introduction to deep learning, but the practical part is discouraging since the "deep learning" part of practical assignments is usually given rather than asked to develop individually.

автор: Anupkumar M

•Oct 11, 2018

Too much mathematical

Some of the instructors were tough to follow

автор: Jeremy C

•Feb 04, 2020

You either need to understand Deep Learning, in which case the explanations are very bad; or you already know Deep Learning a bit; in which case the course doesn't bring anything.

Generally, the instructors are hard to understand, it goes from 0 to 100 in a second.

They also speak with a strong accent which doesn't help the understanding.

If you want to complete the Specialization, maybe follow it and accept to lose your time and money.

Otherwise, skip this and focus on better courses

автор: Ivan M

•Oct 14, 2019

Frankly speaking, I want to set 3 or 2 stars because of:

1) Many non-documented issues which I have writing code for assignments.

2) Material have been made in many foreign languages, but Russian is forgotten and it dissapointed me (hello from Moscow!)

3) Some task descriptions are not actual.

4) Coursera notebooks version is not equals github version (I checked it in GAN).

But hard to learn easy in battle, right? I learn more when try to pass Numpy NN, GAN, LSTM and etc in spite of material, English (I realise that it is very difficult task to fit a lot of material in 5/10/15 minutes. Alexander Panin tried to do it=)). It was very hard, but I did it. I realised that the authors of the course have many important projects and haven't enough time for the courses. So, I want to wish them success in their job and continue work on this course. I believe that they can do better. That's why I set 5 starts. Good luck!

автор: Siddhartha D

•Mar 31, 2018

Course contents are good. Assignments are hard but you get to understand the intricacies of the workings of different types of neural networks and its really fun to do. There are few cases where the assignments require a GPU to work efficiently. I think Coursera should sign up with GPU cloud vendors for deep learning courses. Although peer grading process can be really helpful, I absolutely dislike it. In one instance, my assignment was marked as not runnable by one of the peers while other peers have marked it as runnable and had awarded scores for the other sections of the assignment. But, I had to resubmit the assignment in order to get the full score and it took a while for it to get reviewed as not many peers are available. In some cases, one might have to switch the session. Overall, I highly recommend the course as there's quite a lot to learn from it. Thanks.

автор: Ayush T

•Jul 26, 2018

I think this is the best course on Deep Learning on Coursera. It has flavours of various domains of Deep Learning like CNN, RNN, AutoEncoders and GAN's. The pace of this course is moderate which makes it easy to follow if you know a couple of thing about Deep Learning in advance. Definitely, this course is not for those people who are at a very initial stage or with no knowledge of learning Machine Learning. The assignments which are part of the assignment are really well chosen. This course makes you explore the subject on your own. But still the domain of Deep Learning is huge so there is still a lot to learn.

автор: Samuel Y

•Jan 15, 2018

Very fast and solid course, requiring in-depth knowledge and hard working. Especially the most criticized program assignment part, some is not well detailed and guided (even broken), but it is also partly realistic to mimic actual machine learning project development. It might also take days to tune and try to beat some required passing-level. Fix it yourself is really helpful to master the essence. Running those notebooks locally or in own server env with GPU support is strongly recommended to avoid wasting hours to find coursera kernel dead during training.

автор: khirod

•Apr 16, 2020

It was definitely challenging but at the end it really boosted my confidence as I completed all the lectures and their respective quizzes and assignments. The discussion forums could be more active and helpful I felt.

Finally I want to thank the instructors for designing this course and for all the lectures. There were few videos though which eluded my senses and I had to refer to some online videos to understand the concepts. But if someone has worked previously in similar space, I am sure they won't face any difficulty.

автор: Rabia

•Dec 31, 2019

This was a great course with a lot of hands-on programming time. I liked that the programming assignments didn't have a lot of hand-holding and I ended up learning a decent amount of numpy/tensorflow/keras on my own. It would have been better to have a little more guidance in terms of functional requirements for some of the later assignments which would have saved some unnecessary frustration. But overall it was awesome - looking back on it, I'm amazed at the breadth of material they covered.

автор: Shervin S

•Aug 16, 2019

Thoughtful course with good examples and code. Instructor presentations and graphics used were very organized and clear. Assignments are fairly simple, in terms of work required, but they require you to understand the context and reading through the code is useful. The forum was fairly useful, too.

Some further comments explaining code blocks and practices would have made this experience complete.

автор: Niculae I

•Feb 05, 2018

I guess for ML beginners this course is hard, because some of the lectures are pretty succint and you must figure out by yourself what is going on. But that helps too to understand better some issues. And at least for me the estimated time for the assignments was a bit too optimistic. Still I like the course and learned a lot of new things, altough I was not really new to this matter.

автор: nithin k m

•Apr 17, 2020

There aren't many Courses as this which gives us detailed understanding of Why things Work and Do not Work and What can you do to make them Work. Their theory explanation and practical application's of AutoEncoder's and RNN's is highlight of this Course which aren't offered by many. In loved the projects which do involve every small detail and helped me in Office-Work.

автор: Kelvin L

•Mar 12, 2018

This program is more suitable to those who already have mid level knowledge about the nuts and bots of Deep Learning and looking for hands-on opportunities to advanced skills. Having said that, the projects are really rewarding.

The main problem of this program is that. the teaching is very brief and there's no supporting resource at all, except the discussion forum.

автор: Dalton H

•May 24, 2019

This course was great. I thought the lectures were good, and the quizzes are good at testing your knowledge, but the bets part of the course comes from the assignments. The assignments were both fun and interesting, and allowed me to try different tasks I would have been too intimidated to try otherwise (such as GANs). I really enjoyed this course.

автор: Kristiyan D

•Apr 26, 2018

I didn't watch the videos as I wanted to try my current know-how on the assignments directly, but I can only recommend doing them, as they will provide you with great guidelines on implementing and training different types of neural networks. Even for a fairly experienced data scientist, the assignments were compelling enough.

автор: Eric A S

•May 21, 2018

This is an amazing course, though I would not recommend it to people who are new to machine learning. If you are familiar with the basics, this course is a great intro to more advanced topics, which are explained in easy to understand terms. The assignments are not easy and a lot of work is required, but it is well worth it.

автор: Ivan K

•Dec 14, 2017

I like the course, it gives nice overview of neural nets, frameworks and general implementation approaches. It's a bit time consuming if you're using commodity laptop to train models, but very realistic at the same time. There were a couple of issues with programming assignments, but I'm still giving the course solid 5.

автор: Jorge

•Aug 07, 2019

Sometimes it's hard to follow, since it is more advanced machine learning than introduction, but that's not bad. It gives a general vision of how machine learning solves different problems. Assigments are truly demanding but, again, that's not bad. Resolving them guarantees that you have learned concerned concepts.

автор: Michael B

•Nov 11, 2018

Excellent course which introduces the core concepts of deep learning. However, it is not for the absolute beginner. If you have a good understanding of programming in Python and have done some other introductory deep learning courses, you should be able to complete this course without too much trouble.

автор: Milos M

•Feb 23, 2019

This course goes deep in some areas of Deep Learning that other courses seem to skip, I like the extensive math explanation. Some of the quiz questions as well as project assignments were not formulated very well but overall I like this course, and I would recommend it to intermediate level student.

автор: Tolga K

•Mar 22, 2019

It's one of the best courses I take about Deep Learning. Of course there are some issues as there are in all courses, but they are minimal. I got very important insights from this course and instructors know subjects well. Throughout the course I never suspected about it and money I spended.

автор: Bob F

•Mar 09, 2018

This course provided a great introduction to deep learning with TensorFlow and Keras. The lecturers did an excellent job explaining concepts and techniques and the programming assignments were perfect for getting started with implementing deep learning models. Thanks for an amazing class!

автор: Gary S

•Jun 07, 2019

Excellent course. Covers the material in just enough detail to get you started applying deep learning to your own projects. Jupyter notebooks help tremendously as an entry point for you to learn Tensorflow, Keras, and Numpy. Looking forward to the other courses in the specialization.

автор: Guy G

•Aug 05, 2019

Great course. I found it very cost-effective for providing a broad knowledge about DL, as it covers many topics in a relative short time - providing clear and concise explanations, experimenting with a variety of architectures, and how to utilize them for solving different tasks.

- Искусственный интеллект для каждого
- Введение в TensorFlow
- Нейронные сети и глубокое обучение
- Алгоритмы, часть 1
- Алгоритмы, часть 2
- Машинное обучение
- Машинное обучение с использованием Python
- Машинное обучение с использованием Sas Viya
- Программирование на языке R
- Введение в программирование на MATLAB
- Анализ данных с Python
- Основы AWS: введение в облачные приложения
- Основы Google Cloud Platform
- Обеспечение надежности веб-сервисов
- Разговорный английский язык на профессиональном уровне
- Наука благополучия
- Научитесь учиться
- Финансовые рынки
- Проверка гипотез в здравоохранении
- Основы повседневного руководства

- Глубокое обучение
- Python для всех
- Наука о данных
- Прикладная наука о данных с Python
- Основы бизнеса
- Разработка архитектуры на платформе Google Cloud
- Инженерия данных на платформе Google Cloud
- От Excel до MySQL
- Продвинутое машинное обучение
- Математика в машинном обучении
- Беспилотные автомобили
- Блокчейн для организаций
- Бизнес-аналитика
- Навыки Excel для бизнеса
- Цифровой маркетинг
- Статистический анализ в здравоохранении на языке R
- Основы иммунологии
- Анатомия
- Управление инновациями и дизайн-мышление
- Основы позитивной психологии

- ИТ-поддержка Google
- Специалист IBM по привлечению клиентов
- Наука о данных IBM
- Прикладное управление проектами
- Профессиональная сертификация IBM в области прикладного ИИ
- Машинное обучение для Analytics
- Пространственный анализ данных и визуализация
- Проектирование и управление в строительстве
- Педагогический дизайн