PyTorch is one of the top 10 highest paid skills in tech (Indeed). As the use of PyTorch for neural networks rockets, professionals with PyTorch skills are in high demand. This course is ideal for AI engineers looking to gain job-ready skills in PyTorch that will catch the eye of an employer.
AI developers use PyTorch to design, train, and optimize neural networks to enable computers to perform tasks such as image recognition, natural language processing, and predictive analytics. During this course, you’ll learn about 2-D Tensors and derivatives in PyTorch. You’ll look at linear regression prediction and training and calculate loss using PyTorch. You’ll explore batch processing techniques for efficient model training, model parameters, calculating cost, and performing gradient descent in PyTorch. Plus, you’ll look at linear classifiers and logistic regression. Throughout, you’ll apply your new skills in hands-on labs, and at the end, you’ll complete a project you can talk about in interviews. If you’re an aspiring AI engineer with basic knowledge of Python and mathematical concepts, who wants to get hands-on with PyTorch, enroll today and get set to power your AI career forward!
DD
Excellent Course. I love the way the course was presented. There were a lot of practical and visual examples explaining each module. It is highly recommended!
SY
An extremely good course for anyone starting to build deep learning models. I am very satisfied at the end of this course as i was able to code models easily using pytorch. Definitely recomended!!
ME
this course provides a very good and cohesive introduction to Neural Networks. I learned a lot during my journey and I recommend it for anyone interesting in the field.
SE
Wonderful course!!! Best among all the courses under AI Engineer Certificate by IBM. Deep learning always haunted me with the maths involved but now I get a very good start with this.
D
The explanation is simple and understandable. They explained deep neural networks so beautifully with PyTorch. Thank you very much for this course IBM.
RA
This is not a bad course at all. One feedback, however, is making the quizzes longer, and adding difficult questions especially concept-based one in the quiz will be more rewarding and valuable.
TG
Very intensive course. Could do more training labs. But this is definitely a very dense course. Extremely helpful to get started on ML/Deep Learning.
AF
Excellent course, works its way through basics to fully fledged machine learning models at a good pace. A few of the examples used in the lab code throw errors, these should be rectified
JA
A well curated course filled with stuff essentially needed to acquire the knowledge of Deep Neural Networks with PyTorch and encompasses the domain of practical labs as well
YY
Not only did I gain the basic knowledge of deep learning, but also learned Pytorch. It is a good course, however, there is still a lot more to go in the area of Deep learning,
KD
The right level of detail so that you can dive in. I wish there had been a week to cover RNNs as well though, in particular the best way to handle variable length sequences for RNNs :)
MM
Pros: The course is extremely well structured. The presentations are very informative and clear also well explained.Cons: The assignments and quizzes are not challenging at all
显示：20/418
In general, this course is very useful and I have learned a lot.
But...
A large amount of information has been compressed in a short period of time. The synthesized speech runs too fast. Slides on videos also change too fast. Some of them appear less than a second. A learner has to pause or even rewind a video to catch and explore them for understanding.
Multiple errors in lab solutions (I would call them even bugs). Some of the proposed solutions do not follow requirements specified in preceding cells.
Wrong information in slides. For example, 'hidden layers' instead of 'neurons in the hidden layer' or 'hidden neurons'.
Too many spelling errors in videos, quizzes and descriptions apparently made by non-native English speakers. For example, two instead of too, ture instead of true, supper instead of super, rergresstion instead of regression etc.
Technical issues with labs appear too often - cannot start the server or unavailable at all for multiple days, broken conda installation due to outdated or incompatible module versions (in particular, torchvision and pillow).
I was expecting much more accuracy from a course led by IBM. An editor would be recommended to thoroughly review all the slides, quizzes and notebooks of this course.
Horrible slides, instructor's monotonous voice, typos in exercises, and explanations are inadequate. Course is a rip off at 50 dollar a month.
Still a decent course but compared to other courses in this series, both the content and the
presentation of the content really lack clarity.
This is not a bad course at all. One feedback, however, is making the quizzes longer, and adding difficult questions especially concept-based one in the quiz will be more rewarding and valuable.
While the subject of this course is interesting, the general quality of the course materials is sub-standard of what I am used to on Coursera. I posted a question on the forum that the staff never bothered to answer. I used to a much better quality from Coursera.
This course had many flaws including that at the most basic it was riddled with errors, typos, and formatting issues.
Some more specific feedback is that this course seemed overly preoccupied with explaining math concepts or neural net architecture at a high level and glossing over much of the actual pyTorch specific programming.
The organization of the lectures make no sense, with separate lectures and labs for single class and multiclass versions of various models even though the functions all were built to handle multiple dimensions and so there was really no difference. Additionally because the lectures, lab, and quiz used all the same examples this means we would see the exact material presented over and over with no clear pedagogical reason.
Additionally the course seemed overly preoccupied with OOP to the point of replicating the functionality of several built in pyTorch classes obfuscating the actual material with no clear reason given for why we were creating our own version of extant classes.
Lastly, the quizes almost never asked any questions about pyTorch. Most of them were just the most basic questions about comprehending reading code. Things like "if input = 3 how many inputs are there?" or "which option is used for He initialization" and the options are like "He initialization or Xavier"
A terrific overview of PyTorch. I was especially amazed by the lab notebooks where the author went above and beyond to plot everything in a useful way. This allowed the student to visualize everything that was going on under the hood. In each notebook, there was also multiple ways of showing how to accomplish a task whether it be coding manually or using a PyTorch function to simplify. I appreciate seeing it both ways as it really demystifies the black box of Deep Learning libraries.
The main reasons i gave 5 starts:
1 There is simply a lot of content in this course
2 You can tell that the explanations were thought through and that reflects in the quality of the content
3 The labs are super helpful and presented in a very understandable way
Sure the course doens't cover some topics such as recursive neural networks, but you won't be disappointed unless you are looking for a very very technical course on NNs
A very excellent course to get introduced to PyTorch from bottom up.Also the lectures for Neural Networks and CNNs were short but really excellent and highly intuitive.These short lectures are an excellent way to learn concepts of Neural networks.Would have loved to see a week dedicated to sequence models.The instructors have really really done a fantastic job.
An extremely good course for anyone starting to build deep learning models. I am very satisfied at the end of this course as i was able to code models easily using pytorch. Definitely recomended!!
It was a LONG course, very packed with info. But, I feel like I certainly learned a lot and have a great foundation for further learning.
Amazing, really informative and helps a lot !!! really liked this course and would recommend this to anyone interested in Deep learning!
It is freeaaakin hard if you take the whole IBM AI ENGINEERING Professional Cert in the duration of a trial period.
Lots of errors in the questions and answers, annoying content structure, bad videos (speed, cadence, auto-generated voice that consistently mis-pronounces things). Labs that are identical to the videos. No context setting or understanding beyond trivial mechanics.
Even worse, the quizzes contain typing/syntax errors that you have to ignore and then suddenly some of the quizzes contain errors that you must not ignore.
This is a ridiculuously bad course and I have no idea how it got to getting this many good ratings.
ABSOLUTE WASTE OF TIME. CHOOSE A DIFFERENT COURSE!
I am very disappointed with the quality of the course materials. The videos are recorded with what sounds like a text to speech system or a voice over done by a voice actor who does not really understand the subject matter and lacks personality.
It's hard to understand as it all runs at the same pace and there isn't sufficient time given to specific concepts that may take a shorter or a longer time to sink in depending on their complexity. It's just a constant speed monologue without any real feeling or passion in the subject matter.
Very well done course! The concepts are pretty clearly explained. Sometimes the labs have instructions that are a bit misleading but it's a very minor issue. I really enjoyed the instructor using colored blocks as a tool to explain codes!
One of the best courses I've taken. Everything was really easy explained, step-by-step, with nice slides and lost of explanations. It is really clear and starts from the very beginning. I'll totally recommend it!
this course provides a very good and cohesive introduction to Neural Networks. I learned a lot during my journey and I recommend it for anyone interesting in the field.
It was a very informative and interesting lecture. I learn a lot about the details when using PyTorch to build and train a deep neural network. I am so thankful.
Awesome! This course gives me the basic workflow for using machine learning technique in my research! The materials in the form of Jupyter lab really help!