subject
Intro

Udacity: Deep Learning

 with  Arpan Chakraborty and Vincent Vanhoucke
**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 develop a clear understanding of the motivation for deep learning, and design intelligent systems that learn from complex and/or large-scale datasets.

We’ll show you how to train and optimize basic neural networks, convolutional neural networks, and long short term memory networks. Complete learning systems in TensorFlow will be introduced via projects and assignments. You will learn to solve new classes of problems that were once thought prohibitively challenging, and come to better appreciate the complex nature of human intelligence as you solve these same problems effortlessly using deep learning methods.

We have developed this course with Vincent Vanhoucke, Principal Scientist at Google, and technical lead in the Google Brain team.

***Note**: This is an intermediate to advanced level course offered as part of the [Machine Learning Engineer Nanodegree](https://www.udacity.com/course/machine-learning-engineer-nanodegree--nd009) program. It assumes you have taken a first course in machine learning, and that you are at least familiar with supervised learning methods.*

Why Take This Course?
Deep learning methods are becoming exponentially more important due to their demonstrated success at tackling complex learning problems. At the same time, increasing access to high-performance computing resources and state-of-the-art open-source libraries are making it more and more feasible for enterprises, small firms, and individuals to use these methods.

Mastering deep learning accordingly positions you at the very forefront of one of the most promising, innovative, and influential emergent technologies, and opens up tremendous new career opportunities. For Data Analysts, Data Scientists, Machine Learning Engineers, and students in a Machine Learning/Artificial Intelligence curriculum, this represents a rarefied opportunity to enhance your Machine Learning portfolio with an advanced, yet broadly applicable, collection of vital techniques.

Syllabus

**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.
44 Student
reviews
Cost Free Online Course
Pace Self Paced
Subject Deep Learning
Institution Google
Provider Udacity
Language English
Hours 6 hours a week
Calendar 12 weeks long

Disclosure: To support our site, Class Central may be compensated by some course providers.

+ Add to My Courses
FAQ View All
What are MOOCs?
MOOCs stand for Massive Open Online Courses. These are free online courses from universities around the world (eg. Stanford Harvard MIT) offered to anyone with an internet connection.
How do I register?
To register for a course, click on "Go to Class" button on the course page. This will take you to the providers website where you can register for the course.
How do these MOOCs or free online courses work?
MOOCs are designed for an online audience, teaching primarily through short (5-20 min.) pre recorded video lectures, that you watch on weekly schedule when convenient for you.  They also have student discussion forums, homework/assignments, and online quizzes or exams.

Reviews for Udacity's Deep Learning
1.7 Based on 44 reviews

  • 5 stars 5%
  • 4 stars 5%
  • 3 stars 7%
  • 2 stars 20%
  • 1 stars 64%

Did you take this course? Share your experience with other students.

Write a review
  • 1
2.0 2 years ago
by Gregory J Hamel ( Life Is Study) audited this course.
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 of neural networks and deep learning (neural networks with multiple layers.). Lesson 3 covers convolutional networks for image recognition and lesson 4 covers recurrent networks and issues dealing with text data. This course assumes you have intermediate Python programming experience and basic knowledge of machine learning, statistics, linear algebra and calculus.

Each lesson in the course consists of a series of short video lecture segments with occasional comprehension questions and breaks to apply topics discussed in programming assignments. The video quality itself is good and the lecture quality is adequate, but the lecture segments are very brief, with most lasting around a minute or less. The sum total of the video conten
Read more
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 of neural networks and deep learning (neural networks with multiple layers.). Lesson 3 covers convolutional networks for image recognition and lesson 4 covers recurrent networks and issues dealing with text data. This course assumes you have intermediate Python programming experience and basic knowledge of machine learning, statistics, linear algebra and calculus.

Each lesson in the course consists of a series of short video lecture segments with occasional comprehension questions and breaks to apply topics discussed in programming assignments. The video quality itself is good and the lecture quality is adequate, but the lecture segments are very brief, with most lasting around a minute or less. The sum total of the video content in the third lesson on convnets is less than 15 minutes. The programming assignments, which use a popular neural network library called TensorFlow, are lacking in instruction and involve either running large chunks of provided code or working on open-ended questions. You likely won't be able to make much progress on the assignments without prior knowledge of machine learning and TensorFlow or doing a lot of extra research outside of the course materials. The programming problems also require significant computing resources; my laptop with 8GB of RAM ran out of memory when running the provided code in the first assignment.

Deep Learning is a shallow course that is akin to reading CliffsNotes instead of a textbook: you'll learn some terminology and be exposed to some interesting concepts but its abbreviated coverage is likely to confuse students who are new to neural networks while leaving more experienced students unsatisfied. 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.

I give Deep Learning 2 out of 5 stars: Disappointing.

*If you're interested in learning about the topics this course introduces in much more depth, check out the video lectures and course materials for CS231n, a deep learning course focused on image recognition offered by Stanford.
50 people found
this review helpful
Was this review helpful to you? Yes
1.0 6 months ago
by Andrew Denis dropped this course.
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 spend a too much time and effort on a course being given away. However, it should at least follow good instructional design principles in terms of what is being presented, how its presented, and subsequently how to test and reinforce the materials.

Unfortunately, this is one of the worst eLearning courses I have ever taken; and it definitely keeps me from considering spending any money on other Udacity courses. In fact, it has so many issues that I cannot even justify wasting time learning. From errors and omissions that will teach people inaccurate information, to suboptimal and wrong approaches recommended for basic ML and related problems, as well as quizzes that pretty much illustrate how NOT to tr
Read more
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 spend a too much time and effort on a course being given away. However, it should at least follow good instructional design principles in terms of what is being presented, how its presented, and subsequently how to test and reinforce the materials.

Unfortunately, this is one of the worst eLearning courses I have ever taken; and it definitely keeps me from considering spending any money on other Udacity courses. In fact, it has so many issues that I cannot even justify wasting time learning. From errors and omissions that will teach people inaccurate information, to suboptimal and wrong approaches recommended for basic ML and related problems, as well as quizzes that pretty much illustrate how NOT to try to reinforce learning; I found it impossible to use-- let alone recommend.

While I didn’t expect a $1,000 course for free, since I was reviewing it for others in need of AI/ML/DL instruction, I hoped it would be a lot more professionally done than it was. I would NEVER put something like this out myself, whether it was free or not-- people’s time and abilities are just too precious to waste or partially derail. GIGO.

We spend between $25K-50K per year on instructional materials (e.g. from Lynda.com and UDEMY on the low-end, to personalized instruction on the high end), , and even the cheapest ones are so much better than this. We have helped create online instruction for online and corporate clients for over 30 years, and this level of instruction is like a throw-back to the early days of “multimedia-based” eLearning. It lacks consistency, accuracy, completeness and any real adherence to well-defined, well-accepted instructional standards and practices.

If Udacity cares (and I see that there are plenty of others who have commented negatively on several of the things I observed and noted below), here are some of the observations:

The questions have no contextual definition, are vague in terms of what level or type of answer is being looked for, and mostly serve to disrupt learning flow, rather than reinforce it.

The support and related materials have errors in them-- even things as simple as summation series definition. That is just sloppy and serves to further undermine confidence in the rest of the materials.

There is a lack of consistency inherent to the level of instruction, which jumps from wasting time explaining material that is widely recognized as self-evident, to making assertions that are either unsupported or unsupportable.

The relations between the instructional materials, the quizzes and the reinforcement learning elements are as disjunct as I have ever seen on “professional” instructional materials.

I wanted to finish reviewing this as part of a more in-depth online Web review for an article, but it is just too painful. I may try to have someone else try to get through it.

My only question is whether this is considered a representative level of quality for Udacity Artificial Intelligence instruction, or is just an example of “you get what you pay for”; and since it is free, there is much less care and oversight given to its quality. I can name many dozens of YouTube vlogs that are much better than this in terms of what they teach and how, and they are also virtually free.
Was this review helpful to you? Yes
1.0 2 years ago
Anonymous audited this course.
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 the "Deep Learning" class. In short, "Deep Learning" amounts to little else than a laundry list of methods and concepts of Deep Learning without sufficient instructions on understanding and applying these.

"Deep Learning" is rated as a advanced class and has a long list of requirements. But even taking these into consideration, the class itself does not provide sufficient explanations for new concepts introduced here. I understand that it is important to have the skills to obtain additional resources for challenging concepts, but "Deep Learning" is clearly lacking substance as concepts are introduced very superficially in about 5 min before you are expected to implement these methods in assignments. In the end, you likely end up
Read more
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 the "Deep Learning" class. In short, "Deep Learning" amounts to little else than a laundry list of methods and concepts of Deep Learning without sufficient instructions on understanding and applying these.

"Deep Learning" is rated as a advanced class and has a long list of requirements. But even taking these into consideration, the class itself does not provide sufficient explanations for new concepts introduced here. I understand that it is important to have the skills to obtain additional resources for challenging concepts, but "Deep Learning" is clearly lacking substance as concepts are introduced very superficially in about 5 min before you are expected to implement these methods in assignments. In the end, you likely end up spending hours on additional research using outside resources before you will be able to solve most of the problems stated in the assignments, which is fine, but begs the question what the benefit of taking this Udacity class is.

Skip.
3 people found
this review helpful
Was this review helpful to you? Yes
1.0 10 months ago
Anonymous partially completed this course.
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 3rd party resources they link to. Basically you pay $400 for a list of links to external resources, access to forums and projects that are 90% already done for you.

Most of the content and example code is built in a different version of python than the course requires and using different libraries so is of questionable value

It is also NOT a learn at your own pace course but instead a deadline based one which makes it worse.

I have taken other udacity courses that were amazing. This one is a waste of time

Was this review helpful to you? Yes
1.0 a year ago
Anonymous dropped this course.
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. https://www.kadenze.com/courses/creative-applications-of-deep-learning-with-tensorflow/info
2 people found
this review helpful
Was this review helpful to you? Yes
1.0 a year ago
Anonymous is taking this course right now.
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.
1 person found
this review helpful
Was this review helpful to you? Yes
1.0 a year ago
by Anshul Chauhan partially completed this course.
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.
1 person found
this review helpful
Was this review helpful to you? Yes
1.0 7 months ago
Anonymous is taking this course right now.
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.
Was this review helpful to you? Yes
1.0 a year ago
Anonymous dropped this course.
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.
2 people found
this review helpful
Was this review helpful to you? Yes
2.0 a year ago
Anonymous completed this course.
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.
1 person found
this review helpful
Was this review helpful to you? Yes
1.0 7 months ago
Anonymous is taking this course right now.
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.
Was this review helpful to you? Yes
2.0 2 years ago
Anonymous partially completed this course.
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.
1 person found
this review helpful
Was this review helpful to you? Yes
1.0 a year ago
Anonymous partially completed this course.
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.
Was this review helpful to you? Yes
4.0 a year ago
Anonymous partially completed this course.
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.
Was this review helpful to you? Yes
1.0 a year ago
Anonymous dropped this course.
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.
0 person found
this review helpful
Was this review helpful to you? Yes
2.0 7 months ago
by Daniel Campos is taking this course right now, spending 5 hours a week on it and found the course difficulty to be hard.
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."
Was this review helpful to you? Yes
5.0 a year ago
Anonymous completed this course.
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.
Was this review helpful to you? Yes
1.0 11 months ago
by Jean-louis Queguiner dropped this course.
Unclear and not business oriented, I would recommend fast.ai instead. This course is too theorical and too fuzzy.

I feel like the teacher is too high in the sky to teach to noobs
Was this review helpful to you? Yes
1.0 7 months ago
Anonymous dropped this course.
Massively disappointing and totally unlike Udacity's other engaging and incredibly effective programs. If this is the direction the company is heading in with their education, it would be a major blow to MOOCs generally.
Was this review helpful to you? Yes
1.0 11 months ago
Anonymous dropped this course.
Amazingly obscure and incomprehensive content. the teaching and pedagogy is really bad compared to other Udacity courses. better not waste your time on it!
Was this review helpful to you? Yes
  • 1

Class Central

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

Sign up for free