Deep learning is revolutionizing many fields, including computer vision, natural language processing, and robotics. In addition, Keras, a high-level neural networks API written in Python, has become an essential part of TensorFlow, making deep learning accessible and straightforward. Mastering these techniques will open many opportunities in research and industry.
You will learn to create custom layers and models in Keras and integrate Keras with TensorFlow 2.x for enhanced functionality. You will develop advanced convolutional neural networks (CNNs) using Keras. You will also build transformer models for sequential data and time series using TensorFlow with Keras. The course also covers the principles of unsupervised learning in Keras and TensorFlow for model optimization and custom training loops. Finally, you will develop and train deep Q-networks (DQNs) with Keras for reinforcement learning tasks (an overview of Generative Modeling and Reinforcement Learning is provided). You will be able to practice the concepts learned using hands-on labs in each lesson. A culminating final project in the last module will provide you an opportunity to apply your knowledge to build a Classification Model using transfer learning. This course is suitable for all aspiring AI engineers who want to learn TensorFlow and Keras. It requires a working knowledge of Python programming and basic mathematical concepts such as gradients and matrices, as well as fundamentals of Deep Learning using Keras.
VH
This course is the best out of all courses in the specialization, the pace of the speaker was perfect.
RR
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.
KG
I have seen a lot of people explaining different things in Deep Learning, but I must admit, this course should be given 10 on 10 for covering everything theory to code, basics to advanced.
TJ
I expected some more explaination for the concepts. However from tensorflow website, more could be learnt.
MG
very well-constructed course for deep learning students. Really enjoyed. Many thanks for IBM
BK
It is a very detailed course for those looking for learning more about Keras and Tensorflow.
MW
This course had a best and fast pace understanding for ANN, DNN, RDM and Autoencoders with Tensorflow
RC
Good an simple videos to understand the concept. The notebooks are very detailed and give a second layer of knowledge with practical example
ZR
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!
JT
TensorFlow is fantastic! this course is great to learn the very many applications of the library.
RB
Excellent course to get started with tensorflow and deep learning.Really enjoyed the course.
XH
The course concepts are not in-depth enough, and the server for Jupyter notebook running is way too slow...
Showing: 20 of 228
This course is incomplete, and is NOT recommended.
It uses Tensorflow 1, which is outdated now - should be updated to use Tensorflow 2.
It does not provide practice sessions.
Week 5 - Autoencoder - have no audio, no captions, nothing.
There is no final exam to ensure our competence. No labs we need to be graded on.
This is not a worthy Coursera course. It needs to be withdrawn and updated.
The codes need to be updated for TensorFlow 2.0.
course needed to be updated for labs. Now Google moved to Tensorflow 2.0 this year.
Mostly trivial quiz questions and no graded practical work. The certificate is therefore not worth very much.
There are 2 main problems with this course:
1 All the codes are for tensorflow version 1 and not 2 which essentially makes them outdated since the new version of tensorflow is quite different from the previous
2 All the explanations are very high level and will leave you with many questions. In short you cna learn as much if not more by watching any youtube videos on each of the topics
In general, the course seems to have been rushed out and the material is ridiculously slim. There is really no reason to take this course. You'll end up frustrated by the simplistic explanations and the fact that you are learning code which won't be relevant in a couple months.
Once again I am so surprised to see a reputable company such as IBM put their name on a product which is frankly embarrassingly bad. There is no way this course would be rated 5 starts by any human being which leads me to believe that they manipulate the scores with fake reviews.
The syllabus of this specialization is supposed to be rich; nevertheless, the lectures are not good at all. They mostly read the codes without diving into a proper explanation. The theory background is poor, and the labs don't teach you how to deal with real datasets, just random numbers, nor do they teach you how to implement an entire pipeline of code, just chunks of it without any scope (It seems to me). What could you supposedly expect from modules with lectures of 3 min - 8 min (tops)? I don't recommend this course if you don't have a strong NN background.
This course is a joke. It's a brief overview of a few types of models. Also there is no sound in half the videos.
Good content. A bit too fast on some complex concepts and missing audio for the last lecture but great lecturer.
Teaches more on Deep Learning models but less in TensorFlow
Lack of content, quizzes were poor, no sound or transcript on 2 videos. Took about 2 hours total.
needed more focus on coding and explanation of codes
Videos are good, but lack of graded coding practice is a big issue with this course. I barely knew how TensorFlow works before starting this course... and this hasn't changed after I finished with 100% grade.
I am not sure if no final assessment is a good idea. For the depth of the course it can possibly a major graduation killer but for practical reason you should put that back so people get to be serious with this course.
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!
This is just introductory course, wish to see more content and in details concept. Too short introduction
It is very good to explain concept of Deep Learning by Example , it is so clear, and better understand
It helped me to understand how TensorFlow can be used to build the neural networks
A concise and comprehensive survey of deep learning models. Great labs (which sometimes don't run in IBM Skills Network. Thanks to IBM Watson Studio which came to the rescue in those cases). The labs reinforce concepts and illustrate Tensorflow coding to run the models. Lecturer is very clear and encouraging in tone. Thanks for the course.
Very clear explanation and well organized course. I give 4 stars because videos of Week 5 are missing the audio and subtitles.
Week 5 lecture video no audio
Lab is not update for tensorflow 2