What courses do you...
 
Share:

What courses do you want to see the deeplearning.ai team build next?  

Page 3 / 4
  RSS

doufulai
(@doufulai)
New Member
Joined: 2 years ago
Posts: 4
07/11/2018 9:36 pm  

Reinforcement Learning and advanced computer vision and natural language processing with Deep Learning!


ReplyQuote
KapilcTechLawyer
(@kapilctechlawyer)
New Member
Joined: 2 years ago
Posts: 1
09/11/2018 2:24 am  

Hi, as a AI and Privacy focused lawyer, I am looking at courses that focus on the interplay of AI, emerging Tech., Regulation and Policy. I am a big believer of “AI for Good”. Thanks. Kapil Chaudhary 


ReplyQuote
AbdulMuqeet
(@abdulmuqeet)
New Member
Joined: 2 years ago
Posts: 1
14/11/2018 7:40 pm  

I would like to see Advance Computer Vision specialization, Haptics, General adversarial Networks, Low-power Deep learning Courses. The last one has much importance if we want to apply deep learning for practical applications. 


ReplyQuote
Larr
 Larr
(@larr)
New Member
Joined: 2 years ago
Posts: 1
15/11/2018 12:20 am  

I will prefer a course on introduction to basic probability theory and linear algebra. And also, reinforcement learning should also be included. Thanks 😊 


ReplyQuote
JohnyBeGood
(@johnybegood)
Active Member
Joined: 2 years ago
Posts: 5
15/11/2018 6:42 am  

-reservoir programming (I need to know more for climate modelling)

-Reinforcement Learning

-How to implement Teacher forcing

-more oriented timeseries forcasting (stock, hydrology...) lessons

-intro to pipeline programming use and good coding pratice in ML

 


ReplyQuote
omyg
 omyg
(@omyg)
New Member
Joined: 2 years ago
Posts: 1
15/11/2018 12:13 pm  

I'd be very happy to learn Reinforcement Learning and Generative Models the deeplearning.ai way 😀 . Some advanced courses in specific topics like Computer Vision and NLP will also be a perfect complementary to the amazing learning journey of deeplearning.ai.


ReplyQuote
rileyrustad
(@rileyrustad)
New Member
Joined: 2 years ago
Posts: 1
19/11/2018 9:14 am  
Posted by: curt.dodds

A course on hyperparameter and architecture search would be a topic interesting enough to take. In particular, implementing GA for both hyperparameter and architecture search and using multiple GPUs for distributing search. Advanced HPC concepts for using GPU clusters to distribute training, using a parameter server, and performing distributed search are also interesting (but understandably expensive). However, a toy problem that runs quickly would still give hands on experience and build confidence for learners who want to utilize these resources.

Seconded! I'd also like to see more practical hyperparameter searching methods explained, distributed trainting, etc. Building on that ask, I think I'd make my request more general and ask for a course on "Deep Learning in the Wild", like practical skills for when you actually use deep learning. I think we come to these courses because we want to hear from people with experience (Andrew and Company) because we respect their opinion and so we don't need to reinvent the wheel. I, and I assume "we", are all looking for "The stuff we can't learn from a textbook or blog post." 

Thinks like setting up your local and/or cloud environment, GPU setup, practical architecture design, hyperparameter search beyond random, Distributed DL paradigms and set up, reading from "Big Data" distributed file systems, how to get unstuck when you encounter a problem that isn't easily fixed by reading Stackoverflow/documentation, maybe even project design (how to ask the right questions before you even get started?). 

I'd propose a capstone or final project to put these skills to use, and the course video content could be some of these commonly, often unaddressed and yet common questions. It's easy enough for us to complete the spoon fed assignments in the coursera specialization, and while it's useful to build some of these things from scratch, we're not actually getting a good feel for what the process and strategy experts use to approach a new problem.


ReplyQuote
imrank1
(@imrank1)
New Member
Joined: 2 years ago
Posts: 1
19/11/2018 11:58 pm  

In addition to what has been mentioned id like to see a  new version of the old Machine Learning course on coursera. 


ReplyQuote
assafb
(@assafb)
New Member
Joined: 2 years ago
Posts: 2
22/11/2018 10:19 am  

* +1 for Reinforcement learning

* (Semi-) unsupervised NNs

* Financial markets and NNs!  While it sounds specific, in sci. papers it leverages so many advanced NN techniques from the every course in the spec and beyond, so it may be a great vehicle for a course on advanced subjects and integration of the entire specialization.  Plus a hot subject by itself  🙂

 

Thanks


ReplyQuote
dpoulopoulos
(@dpoulopoulos)
New Member
Joined: 2 years ago
Posts: 1
04/12/2018 7:53 am  

Unsupervised learning using deep neural networks. RBMs, Autoencoders etc. And of course a course on Generative Adversarial Networks.


ReplyQuote
Alexander Berger
(@alexander-berger)
New Member
Joined: 2 years ago
Posts: 1
12/12/2018 1:14 am  

Would be great to get a course which is based on the real projekt. This can help to show all problems which arise.

And of course Unsupervised learning.


ReplyQuote
mehran97_r
(@mehran97_r)
New Member
Joined: 2 years ago
Posts: 3
13/12/2018 8:13 am  

RNN


ReplyQuote
nickpoerio
(@nickpoerio)
New Member
Joined: 2 years ago
Posts: 1
13/12/2018 2:18 pm  

- Deep Reinforcement Learning

- Unsupervised Deep Learning


ReplyQuote
kbhartiya83
(@kbhartiya83)
New Member
Joined: 2 years ago
Posts: 1
19/12/2018 3:19 pm  

Please build a Generative Adverserial Networks(GANs) course as the top latest research in deep learning is mostly related to GANs.

Since its a recent topic , many like me are unable to understand the core concepts of GANs.

 


ReplyQuote
enzo
 enzo
(@enzo)
New Member
Joined: 2 years ago
Posts: 1
28/12/2018 4:05 pm  

Reinforcement learning, unsupervised learning in all its flavours and applications by TensorFlow shoulb be very appreciated.

I think the style used in DL courses of Andrew Ng is a perfect mix of theory and practice and should be taken as an example.

In my opinion in every course more time should be spent on Keras and TensorFlow exercises because they've not a friendly API interface and are very tough to master!


ReplyQuote
Page 3 / 4
Share:

We use cookies to collect information about our website and how users interact with it. We’ll use this information solely to improve the site. You are agreeing to consent to our use of cookies if you click ‘OK’. All information we collect using cookies will be subject to and protected by our Privacy Policy, which you can view here.

OK

Please Login or Register