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....

创建者 RK

•Mar 01, 2019

Really Great course. I would recommend everyone to take this course but after having some "basic knowledge" of Machine Learning, Deep Learning, CNN, RNN and programming in python.

创建者 YG

•Jan 28, 2018

This is a very hands on Deep Learning class. Like the design of programming assignments a lot. It's very instructive as well as challenging! Great course. I would recommend it!

筛选依据：

199 个审阅

创建者 ashesh gajanan mishra

•May 09, 2019

Its much more informative than the title suggests. A good course to take for someone who already knows basics/theoretical knowledge of machine learning.

创建者 Jun Kunikata

•May 02, 2019

Some programming assignments were not instructed enough, so it's very hard to solve them without discussion forums. But this is good course as a whole.

创建者 Driaan Jansen

•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.

创建者 AGWU Elbby Skermine

•Apr 27, 2019

Learned and liked a lot

创建者 Mohammed Saad Elsayed

•Apr 19, 2019

very detailed , clear and to the point , i loved it

创建者 Erik Grabljevec

•Apr 13, 2019

This course gives a great overview of what can be done with DNNs. Topics are well chosen, clearly presented, and a good level of difficulty.

创建者 Marian Lobur

•Apr 12, 2019

I'm not sure that this course is needed at all. Folks are trying to explain multiple architectures of Neural Networks, without giving an actual understanding why it works. Plus I have a feeling that all of this things are going to explained in next courses of this specialization.

创建者 Swapnil Kumar Bishnu

•Apr 11, 2019

One of the best courses on deep learning . Kudos to the creators.

创建者 Tina Zhu

•Apr 07, 2019

A few typos in the slides, quizzes and in the homework, some of the presenters do not speak very clearly and are hard to follow (which would not be a big problem if they practiced their lectures, cleaned up the transcripts, gave out notes or powerpoint slides.) Quality of the course is much lower than the Stanford ML course on this site.

Coursera Jupyter notebooks keep disconnecting and my computer has trouble training the computation-heavy homework as well. Some of the homework is literally 95% wait for the computer or Coursera notebook to run or restart, 5% actual coding. It makes homework incredibly slow and inefficient for learning. I really want to learn the material and the lecturers are clearly very knowledgeable, but this course has some clear problems.

创建者 Yu Qinyuan

•Apr 07, 2019

Brief but clear lessons for intermediate level students with not-easy assignments. :)