Chevron Left
Back to Building Deep Learning Models with TensorFlow

Learner Reviews & Feedback for Building Deep Learning Models with TensorFlow by IBM

4.4
stars
598 ratings
119 reviews

About the Course

The majority of data in the world is unlabeled and unstructured. Shallow neural networks cannot easily capture relevant structure in, for instance, images, sound, and textual data. Deep networks are capable of discovering hidden structures within this type of data. In this course you’ll use TensorFlow library to apply deep learning to different data types in order to solve real world problems. Learning Outcomes: After completing this course, learners will be able to: • explain foundational TensorFlow concepts such as the main functions, operations and the execution pipelines. • describe how TensorFlow can be used in curve fitting, regression, classification and minimization of error functions. • understand different types of Deep Architectures, such as Convolutional Networks, Recurrent Networks and Autoencoders. • apply TensorFlow for backpropagation to tune the weights and biases while the Neural Networks are being trained....

Top reviews

ZR
Jul 2, 2020

Deep Learning made me feel that there is a way to build models and classify data so easily and in a skillful way. Amazing course!

DO
May 26, 2020

Not so often i wish a course would be longer and more in depth I really enjoyed using TF I'll look some other courses about it

Filter by:

101 - 121 of 121 Reviews for Building Deep Learning Models with TensorFlow

By suman k s

May 19, 2020

Low explanation.

But in this short duration we can't expect more.

By Giorgio G

Jun 25, 2020

Course needs to be updated to Tensorflow 2.0 at least.

By Kabila H S

May 17, 2020

The tensorflow version is outdated

By Rafi J O

Jul 12, 2020

Outdated and not in depth enough.

By Emanuel N

Feb 23, 2021

Falto mas teoria

By Bernardo A P

Aug 26, 2020

No real dataset

By ABOUJAAFAR O

Jun 2, 2020

no applications

By Juho H

May 12, 2020

Disappointing stuff. The videos teach complex stuff like recurrent neural networks (RNNs like LTSM), restricted Boltzmann machines, and autoencoders very quickly - less than 10 minutes per "week" of learning. While the labs are extensive, you don't learn anything as the amount of TensorFlow code is totally intimidating and none of the steps are really explained. You can copy the code, but you won't develop an understanding of it in this course. Not to mention the code is so heavy the Skills Lab times out before the network is trained. Still, if you just want to claim you've done Tensorflow, you can click through the stuff in about 30 minutes per "week" of learning.

By Junsoo P

Sep 22, 2020

The lectures only cover various neural nets and not how to actually implement them on Tensorflow, which should be the gist of the course. Further, the labs are at many places not compatible with the most recent Tensorflow version 2's, and only work for previous Tensorflow version 1's which are quite different. The labs must be re-written for the newest versions given Tensorflow's backward incompatibility.

By Stefan L

Jul 4, 2020

This course was very informative and the labs are really well written.... however the code is SEVERELY out of date. It needs to be updated for TensorFlow 2.0, there is simply no excuse at this point

By Farrukh N A

Jan 13, 2020

First of all it was too complex, unlike the course on PyTorch which focused on both Theory + Practical part. It focus only on theory.

By Pakawat N

May 31, 2020

It is too basic and almost no technical detail about the DNN. It is not good for who have basic knowledge about this before.

By Sowmyashree S

May 2, 2020

The codes should be provided with Tensorflow 2.0. Practical implementation should also be shown.

By César A C

Jun 29, 2020

I think that the labs should have been updated to tensorflow 2.

By Eric

Jan 30, 2020

Way too short in terms of the amount of content

By Julian S

Jun 21, 2020

The Material needs to be updated!

By Ustinov A

Aug 6, 2020

Good videos and bad labs. An old TensorFlow version is used. Therefore all code is useless for the current version of TensorFlow (ver. 2). It had to become the most important part of the specialization for me... There are a lot of topics about problems on the forum. And it's strange that IBM can't change it for a half year.

By Onno v E

Aug 24, 2020

This course is very outdated, it needs to be updated to Tensor Flow 2.0.

There are NO EXERCISES at all, only labs that contain the some content as the video's. I don't think I really learned much during this course, as the course does not dive deep into the models selected for the course.

By Huang-Hsiang L

Sep 12, 2021

The lecture is very horrible and you almost need to learn all the details about tensorflow by yourself, which does not make sense. The lecture should explain those details in a clear and easy-to-understand way so that student can benefit.

By Anas O

Jun 2, 2020

the labs are based on an outdated tensorflow version, also, the instructor is not Alex Akilson as it is mentioned in the course info.

By Martin B

Jun 13, 2020

All the code in the course is obsolete using an old version of TF. The course does not have a project nor a final assignment.