[HN Gopher] Pen and paper exercises in machine learning
       ___________________________________________________________________
        
       Pen and paper exercises in machine learning
        
       Author : beefman
       Score  : 68 points
       Date   : 2022-06-28 21:11 UTC (1 hours ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | arcanus wrote:
       | Some good stuff here! I'm surprised they didn't show many
       | analytical results in neural networks. For example, I like making
       | candidates for research in deep learning derive back propagation.
       | You can show a wide variety of interesting results in single
       | neuron models as well.
        
       | neophocion wrote:
       | Omg what a work of art!
       | 
       | Only comment is that it seems quite heavily focused on graphical
       | models, more bayesian/nn concepts would be great to see in this!
        
         | neophocion wrote:
         | * and bandits/RL
        
       | eachro wrote:
       | I still have yet to use graphical models (in the traditional
       | sense, not including the new age variational inference style
       | neural networks as graphical models) in real life. Am I just
       | completely missing something? Where do people generally find
       | compelling uses for graphical models?
        
       | fernly wrote:
       | I am at a loss to understand how these constitute _machine_
       | learning? The preface says "the exercises are ideally paired with
       | computer exercises..." but I am at a loss to imagine what such
       | computer exercises would look like. Somebody ELI(at least 10)?
        
         | jackpirate wrote:
         | These exercises are writing mathematical proofs that basic
         | machine learning algorithms behave correctly. They are "pen and
         | paper" not because you are manually solving a large equation
         | that a machine would normally solve, but because we don't have
         | automated theorem provers capable of proving interesting
         | machine learning theorems. I would expect a typical 1st year
         | grad student to be using a resource like this.
         | 
         | If you don't understand the purpose of proofs, then this
         | resource is not aimed at you.
        
       | MikeDelta wrote:
       | It it quite detailed, impressive. Brave use of the title font as
       | well.
        
       | ivan_ah wrote:
       | Nice. I only looked at the linear algebra parts (first 20 pages),
       | but very impressed with the detailed solutions.
        
       ___________________________________________________________________
       (page generated 2022-06-28 23:00 UTC)