Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.


Intro to Deep Learning

Google via Udacity

This course may be unavailable.


Machine learning is one of the fastest-growing and most exciting fields out there, and deep learning represents its true bleeding edge. In this course, you’ll get an overview of what deep learning is all about.

Partnering with Vincent Vanhoucke, Principal Scientist at Google, and technical lead in the Google Brain team, we’ll teach you how deep learning builds on machine learning. Then you’ll get a chance to learn more about deep neural networks and advanced architectures such as convolutional networks and recurrent networks.

And if you’d like to dive even deeper into this cutting-edge field, we recommend that you continue your studies with our full-fledged Deep Learning Nanodegree program to get more hands-on experience.



Lesson 1: From Machine Learning to Deep Learning

  • Understand the historical context and motivation for Deep Learning.
  • Set up a basic supervised classification task and train a black box classifier on it.
  • Train a logistic classifier "by hand"Optimize a logistic classifier using gradient descent, SGD, Momentum and AdaGrad.

Lesson 2: Deep Neural Networks

  • Train a simple deep network.
  • Effectively regularize a simple deep network.
  • Train a competitive deep network via model exploration and hyperparameter tuning.

Lesson 3: Convolutional Neural Networks

  • Train a simple convolutional neural net.
  • Explore the design space for convolutional nets.

Lesson 4: Deep Models for Text and Sequences

  • Train a text embedding model.
  • Train a LSTM model.

Taught by

Arpan Chakraborty and Vincent Vanhoucke


1.7 rating, based on 50 Class Central reviews

Start your review of Intro to Deep Learning

  • Udacity's "Deep Learning" is a 4-lesson data science course built by Google that covers artificial neural networks. The first lesson builds up some machine learning background on classification problems, while lesson 2 discusses the basic machinery…
  • Profile image for Andrew Denis
    Andrew Denis
    HORRIBLE QUALITY OF INSTRUCTION -- ERRORS, OMISSIONS AND OTHER ISSUES! - I thought I’d try the free Google Deep Learning course on Udacity. Although I don’t agree with doing things poorly, I can at least partially understand that they don’t want to…
  • Anonymous
    I have taking many classes on Udacity whose instruction quality was exceptional, often employing advanced teaching methods (e.g. actively reflecting on exercises in the "How to Use Git and GitHub" class), so I was shocked about the poor quality of t…
  • Anonymous
    As many have said the course is poorly put together. It was misrepresented as requiring basic python and little math, both untrue (I believe they have revised the requirements now to be more honest). The material is poorly represented, 80% of it is…
  • Anonymous
    This course doesn't go much farther or deeper than what is already on Tensorflow's website. I'd really recommend the Kadenze course on Tensorflow. It is very engaging and full of details and tons of code. The homework is about 90% complete with the rest up to you to fill in, and there are Python notebook transcripts for every lecture that are also very useful.
  • Anonymous
    This is really the worst mooc I've taken so far, and I've taken quite a lot. No real understanding, just rushing over stuff without any theoretical foundation or explanation.
    Really really bad, almost made me angry.
  • Anonymous
    Really bad. Don't take it.
    Really bad. Don't take it.
    Really bad. Don't take it.
    Really bad. Don't take it.
    Really bad. Don't take it.
  • Anonymous
    This course has fallen so far below my expectations that it's difficult to describe my disappointment. Within the first week, I had to stop the lesson, do the Coursera DL course, and eventually return to Udacity to complete the first section. This i…
  • Anonymous
    Very superficial and confusing course. It seems that Udacity did not have a clear target audience in mind: it will not satisfy beginners (too confusing) nor intermediate practitioners (too superficial).
    Besides, the teaching quality is terrible: the videos are too short and dumbed down. They provide many external resources which will make you waste a lot of time.
  • Profile image for Anshul Chauhan
    Anshul Chauhan
    I could not complete it. Its too fast, confusing and boring. The instructor might be a genius but he does not know how to teach.
  • Anonymous
    I would give 0 stars if possible. 600$ for this crap. You get no help. There is just a forum. You can not keep the course if you want to do later also. It is absolute bull shit.
  • Profile image for Kudzai Sean Huni
    Kudzai Sean Huni
    I pity those that dropped out. To take this course, you need bags of guts. & this is the best instructor ever!!! He's motivated, insightful and he makes it look soo easy. I'm currently taking the course. I hope to complete it soon. I'm half-way, &…
  • Anonymous
    In short, the assignments are more interesting and more rewarding than the lectures.

    The lectures lack in depth explanations on the models and the additional tricks like dropout and pooling. I learned much more when spending time on the homework. But I still get the uncomfortable feeling of implementing something I don't have a complete understanding of nor I know how to improve my implementation other than adding layers or playing with parameters.

    The course is not bad if you just want to have a quick overview of the field or how tensorflow roughly works. For an advanced course as it is stated, it is probably better stated as introductory.
  • Anonymous
    I'll rate it 5 stars but I understand why other people are giving it low reviews. When I took this course I was already taking another deep learning mooc that went very slow, so the 2 -4 minute lectures in this mooc were refreshing, it just requires the student to research topics that require a deeper mathematical explanation.
  • Anonymous
    Very bad. Confusing, unclear and made me lose interest pretty much right away.
    Very bad. Confusing, unclear and made me lose interest pretty much right away.
    Very bad. Confusing, unclear and made me lose interest pretty much right away.
  • Anonymous
    After having taken the Coursera Machine Learning course with Andrew Ng, this one is very hard to appreciate. Eluding important explanations, tripping on the maths while overlooking the sense behind it... Pretty disappointed so far. I hope I'll still get something out of it, which at this point is not certain.
  • Anonymous
    It's a good thing that Arpan Chakraborty is a researcher and not a professor in university because it takes more than between 50 seconds and one minute to absorb material in an advanced computer science course.

    This course had a great deal of potential but it is rushed and 90% of the assignments are already done for you, making it difficult to learn from.
  • Anonymous
    I don't think the existing reviews are fair. Overall this is a great course, because though very brief, it really touches the basics of each deep learning methods. The introductions may not be easy to understand for everybody, nonetheless they are extremely insightful.

    I took a star away only because the assignment design sucks. Meanwhile one should still keep in mind that the instructor is amazing.
  • Daniel Campos
    In my opinion, a recent review says it all: "This course seems like a rushed attempt to capitalize on the hottest buzzword in the hottest tech industry, which is a shame because it could have been a good course if it took the time to cover the topics in adequate detail."
  • Unclear and not business oriented, I would recommend instead. This course is too theorical and too fuzzy.
    I feel like the teacher is too high in the sky to teach to noobs

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.