On Wednesday, January 4, 2017 at 1:33:45 PM UTC-5, Edward K. Ream wrote:

>From one page (don't remember which one) I found this series of lectures 
> <https://www.cs.ox.ac.uk/people/nando.defreitas/machinelearning/> from 
> the computer science department at Oxford University.
>

Well.  Googling "deep learning course" leads to this page 
<http://machinelearningmastery.com/deep-learning-courses/>. It contains 
six(!) free online courses.  It contains this quote:

"My best advice is: Do not pick a course and work through it end-to-end."

This seems reasonable to me.  Deep learning is a big, big field.

Near the bottom of the page is a link to the "Deep learning with Python 
<https://machinelearningmastery.com/deep-learning-with-python/>" page. Yes, 
it's one big ad, but it may be a valuable resource.  In particular, it says 
this:

"Deep learning looks like a hard field to get started in. And in many ways 
it is hard to get started. Hard enough that many people try and quickly 
give up. Why? Because they are told that they must already be masters in a 
laundry list of academic disciplines..."

I think the author is on to something. Imo, there is no real need to slog 
through a big chunk of math.  Instead, one can use the Kahn Academy to 
review what's actually needed, as it is needed.  The idea is to work 
backwards, in some sense, from what needs to be known to the relevant 
material.  In other words, one can skip a lot of stuff ;-)

When done this way, all the math study will be properly motivated.  Yes, we 
have to know about gradients, partial derivatives (of various kinds), 
probability distributions, matrix algebra, etc.  But we don't necessarily 
have to *start* with that knowledge. Instead, we should start with the *need 
to know* that knowledge.

EKR

-- 
You received this message because you are subscribed to the Google Groups 
"leo-editor" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/leo-editor.
For more options, visit https://groups.google.com/d/optout.

Reply via email to