Voltar para Introduction to Deep Learning

4.6

1,176 classificações

•

263 avaliações

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

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.

Filtrar por:

por Aswin R

•Mar 13, 2019

Very peripheral teaching. Unable to understand anything from the touch points being covered. Assignments are not at all matching with the course contents.

por Kartoffel

•Jan 18, 2018

Not all teachers speak english well enough. You need to be skilled python, tensorflow, karas developer. They dont explain the algorithms very well and you dont have a text book to look it up yourself..

por Fereydoon V

•Nov 11, 2017

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!

por Roberto M P

•Jan 28, 2018

The lecturer is really bad, he is not clear and his explanations are shallow and vague.

por Akshay N

•Dec 23, 2017

Not a good course.

The lectures are rushed through. At one point towards the end of week one, the lecturer just reads out the mathematical formulae on gradient descent extensions, without giving any background on their interpretation, or any examples.The number of notations used are too many to keep track of.

There are no instructions available on how to tackle assignments in Python (nor any mention of Python language as a pre-requisite).

por Nick

•Feb 23, 2018

Awful. Questions unclear, lecturers struggle with basic english, and typos are everywhere

por Dulat A

•Dec 17, 2017

Quality of lectures were totally disapointing. I watched previous courses from Yandex, which were taught on Russian, and they were much better. At some points, lectures even cannot explain what they want to say. I feel like Yandex have stolen 50$ from me.

por Herbert D

•Mar 04, 2018

This has to be the worst course on Coursera.

por Mohit K

•Sep 07, 2018

This course goes over my head. I found this course 'callous'. Doesn't care about my learning!

por Scott B

•Jun 12, 2019

This course is very poorly designed. The lectures are insufferable, and absolutely zero supplemental content is provided that would make it actually possible to engage in the material in any meaningful way beyond suffering through the prattle and drone of recitation of mathematical concepts. Very disappointing.

por Zhou C

•Aug 12, 2019

The instructions are often unclear and the ipynb files often does not even run.

por Philip G

•Nov 03, 2019

Out dated

O Coursera proporciona acesso universal à melhor educação do mundo fazendo parcerias com as melhores universidades e organizações para oferecer cursos on-line.