[HN Gopher] Yann LeCun's 2021 Deep Learning Course at CDS free a...
       ___________________________________________________________________
        
       Yann LeCun's 2021 Deep Learning Course at CDS free and fully online
        
       Author : MAXPOOL
       Score  : 130 points
       Date   : 2021-11-14 17:04 UTC (5 hours ago)
        
 (HTM) web link (cds.nyu.edu)
 (TXT) w3m dump (cds.nyu.edu)
        
       | foolinaround wrote:
       | What are the prerequisites prior to taking this course? TIA!
        
         | stagger87 wrote:
         | Prerequisites are listed in the second sentence...
        
           | homarp wrote:
           | jupyter notebook for DS-GA-1001
           | https://github.com/briandalessandro/DataScienceCourse
           | 
           | and the syllabus: https://github.com/briandalessandro/DataSci
           | enceCourse/blob/m...
        
       | Mougatine wrote:
       | Shameless plug: I've made a deep learning course oriented with
       | practical content on a wide variety of computer vision topics -->
       | https://arthurdouillard.com/deepcourse/
       | 
       | with slides, google colab, and anki cards
        
         | ahevia wrote:
         | Anki Cards? I'm sold
        
         | mkl wrote:
         | I'll look at this properly when I'm not on mobile, but I
         | noticed some minor issues. A typo that seems to be repeated a
         | few times: "space-repetition" should be "spaced-repetition".
         | There are also several unnecessary capitals in your opening
         | sentence.
        
         | jay3ss wrote:
         | This looks great
        
       | tmabraham wrote:
       | It's important to also credit Alfredo Canziani who organized much
       | of the course.
        
       | clircle wrote:
       | I wonder if students that take this class are better at throwing
       | their pile of data into Tensorflow.
        
         | minihat wrote:
         | This cynical point of view is shared by a number of engineers I
         | know. Another version of it is 'why is it worth learning the
         | calculus of machine learning when that is mostly abstracted
         | away by Tensorflow/PyTorch/JAX?'
         | 
         | To a software engineer accustomed to operating on layers of
         | abstraction far removed from the hardware, this may seem a
         | reasonable point. Why is it worth learning that pesky math,
         | anyway?
         | 
         | I would argue that the machine learning engineers of today are
         | more like electrical engineers than programmers, however. When
         | something goes wrong, you don't have nice warning messages or
         | error catching available to you. Like an electrical engineer
         | with a voltmeter, one must begin probing inputs and outputs
         | each step of the way. Good luck doing that if you do not
         | understand how the components are supposed to work.
         | 
         | YMMV by copying and tweaking others code, but I believe we are
         | still far off from hands free 'autoML'. Just ask anyone who has
         | sent a model to deployment whether AWS autoML was sufficient
         | for them. And whether they needed someone who understands
         | backprop at some point during the model training process.
        
       ___________________________________________________________________
       (page generated 2021-11-14 23:01 UTC)