Chevron Left
返回到 Building Deep Learning Models with TensorFlow

學生對 IBM 提供的 Building Deep Learning Models with TensorFlow 的評價和反饋

521 個評分
107 條評論


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....



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!


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


51 - Building Deep Learning Models with TensorFlow 的 75 個評論(共 107 個)

創建者 Omri


This is a great course and a great instructor. I also loved his course on Machine Learning with Python. My major criticism, relevant also for the course on Keras in the AI Engineering program, is that the lectures and labs are not updated to the new versions of packages. The new versions of Tensorflow, Tensorflow2.0, were changed significantly relative to the version used here. Moreover, Keras in now TensorFlow's official high-level API, which means that the code learned in these courses cannot be used for new data without implementing the new syntax of these libraries. I hope IBM will update the learning material more frequently so these wonderful courses will keep being relevant.

創建者 A A A


The instructor Saeed Aghabozorgi did an excellent job in explaining the concepts in a way everything can be understood easily. However, I still think 5 weeks is not enough for this course, given TensorFlow is more difficult to learn than PyTorch. The basics could be covered in more detail, including the tf.get_variable(), tf.gradient(), calculating gradients and other functions that were used. There could be a lecture for Linear Regression and Logistic Regression and these 2 could be moved to a separate week instead. Also, please upgrade the code to work on TensorFlow 2.1. The current code designed for TensorFlow 1.8 didn't work especially the part where datasets are to be loaded.

創建者 bob n


Four stars because some of the labs (and none of the lectures) have not been brought up to the current version of TensorFlow. There are significant differences between 1.x and 2.x, especially in the paralell processing. I don't expect a course to send me on wild goose chases across the internet having to bring their examples up to current versions. I guess you get what you pay for, no surprise that Big Blue isn't current.

創建者 Michael S


Very interesting material, and easy to follow along. The notebooks are a great resource. I am glad to have been introduced to these concepts. However, I felt this course was too easy and it did not encourage the student to complete projects or any independent work. In any case, this course was worth taking.

創建者 James R


I liked the course; however, there was no sound or transcripts for the last week of the course. This required me to research all the topics that I saw on the screen. Still a good learning experience but put more responsibility on me to learn the topics.

創建者 Edward J


Interesting course but I wish there were more opportunities to add code myself or even a proper task. I was sad not to have videos from Romeo. However, I thought that the explanations of the different deep learning models were very clear.

創建者 Julien P


Excellent notebooks. I don't give 5 stars because the quality of videos could be improved and the quizzes could be made tougher. It is easy to pass the class with a superficial understanding of concepts.



Nice course to introduce you to more advanced neural network algorithms, I wish the evaluations were more challenging and based on practical exercises... there is no final assignment either.

創建者 Hrushit J


It would have been nice if the video tutorials would explain the code section as well, and if there would have been some in-depth teaching of the code part. But this course did benefit.

創建者 Jesus M G G


Videos are good, but the code is more complex than other courses and it needs better description of what is happening, or less complicated code

創建者 Ronan C


Good an simple videos to understand the concept. The notebooks are very detailed and give a second layer of knowledge with practical example

創建者 Xiaoer H


The course concepts are not in-depth enough, and the server for Jupyter notebook running is way too slow...

創建者 Projit C


The coding part was hard to understand. If that part could also be covered in videos as a tutorial.

創建者 Javier R V


It would be grate that the examples have been updated to the TF 2.0 version.

創建者 Patricio V


Good material but almost all the labs are too slow to run properly

創建者 Vishwanathan C


Good introduction to Deep Learning Models with Tensorflow

創建者 Tim d Z


Very informative, could use some more room for practice.

創建者 Mahesh N


Lab content must be updated with latest TensorFlow.

創建者 Armen M


Thank you. thought it's could be more deeper

創建者 Mpho c


no audio in the last learning unit 5.



some questions are a bit confusing

創建者 Bhaskar N S


Met expectations

創建者 Konrad A B


It is ok

創建者 Nagesh R



創建者 Roger S P M


This is a pretty good course on the different types of neural networks and their cousins. The presentation slides are really well done. The examples are programmed in TensorFlow. But the course does not really teach very much about TensorFlow itself. The opening lecture on TF describes it in terms that suggest this was created for TF 1.x, rather than the new structure in 2.x. But that turns out not to be an issue since they go into little detail on TF itself.

The programming examples are really good. However, most of the time, the web site on which they run is usually not working. So you often cannot use the labs in conjunction with the lectures. You have to go back and access the labs sometime when the website is working.