[HN Gopher] Understanding Deep Learning
       ___________________________________________________________________
        
       Understanding Deep Learning
        
       Author : georgehill
       Score  : 107 points
       Date   : 2023-11-26 20:54 UTC (2 hours ago)
        
 (HTM) web link (udlbook.github.io)
 (TXT) w3m dump (udlbook.github.io)
        
       | WeMoveOn wrote:
       | lit
        
       | msie wrote:
       | This book looks impressive. There's a chapter on the unreasonable
       | effectiveness of Deep Learning which I love. Any other books I
       | should be on the lookout for?
        
         | nootopian wrote:
         | https://news.ycombinator.com/item?id=38425368
        
       | ldjkfkdsjnv wrote:
       | I spent a decade working on various machine learning platforms at
       | well known tech companies. Everything I ever worked on became
       | obsolete pretty fast. From the ML algorithm to the compute
       | platform, all of it was very transitory. That coupled with the
       | fact that a few elite companies are responsible for all ML
       | innovation, its oxymoronic to me to even learn a lot of this
       | material.
        
         | drBonkers wrote:
         | What would you recommend someone read instead?
        
           | ldjkfkdsjnv wrote:
           | Better to understand the bounds of whats currently possible.
           | And then recognize when that changes. Much more economically
           | valuable
        
             | probablynish wrote:
             | Do you think there's a better way to do this than spending
             | some time playing around with the latest releases of
             | different tools?
        
         | reqo wrote:
         | Very few things stay the same in Technology. You should think
         | of technology as another type of evolution! It is driven by the
         | same type of forces as evolution IMO. I think even Linus
         | Torvalds once stated that Linux evolved trough natural
         | selection.
        
         | nabla9 wrote:
         | >machine learning platforms
         | 
         | Machine learning platforms become obsolete.
         | 
         | Machine learning algorithms and ideas don't. If learning SVN or
         | Naive Bayes did not teach you things that are useful today, you
         | didn't learn anything.
        
           | xcv123 wrote:
           | Agreed. Look at the table of contents of this book. Whatever
           | fundamental machine learning concepts you learned with SVM or
           | other obsolete algorithms is still useful and applicable
           | today.
        
           | ldjkfkdsjnv wrote:
           | Nobody is building real technology with either of those
           | algorithms. Sure, they are theoretically helpful, but they
           | arent valuable anymore. Spending your precious life learning
           | them is a waste
        
             | xcv123 wrote:
             | So what? The same fundamental machine learning concepts are
             | still relevant to deep learning.
             | 
             | It's almost like arguing that everything you learned as a
             | Java developer is completely useless when a new programming
             | language replaces it.
        
         | HighFreqAsuka wrote:
         | Quite a lot of techniques in deep learning have stood the test
         | of time at this point. Also new techniques are developed either
         | depending on or trying to solved deficiencies in old
         | techniques. For example Transformers were developed to solve
         | vanishing gradients in LSTMs over long sequences and improve
         | GPU utilization since LSTMs were inherently sequential in the
         | time dimension.
        
           | ldjkfkdsjnv wrote:
           | Sure, but if you were an expert in LSTM, thats nice, you know
           | the lineage of algorithms. But it probably isnt valuable,
           | companies dont care, and you cant directly use that
           | knowledge. You would never just randomly study LSTMs now.
        
             | HighFreqAsuka wrote:
             | Transformers have disadvantages too, and so LSTMs are still
             | used in industry. But also it's not that hard to learn a
             | couple new things every year.
        
       | water-your-self wrote:
       | No chapter on RNNs, but one on transformers is interesting,
       | having last read Deep learning by ian goodfellow in 2016
        
         | nothrowaways wrote:
         | Yeah, content looks interesting.
        
         | PeterisP wrote:
         | RNNs have "lost the hardware lottery" by being structurally not
         | that efficient to train on the cost-effective hardware that's
         | available. So they're not really used for much right now -
         | though IMHO they are conceptually sufficiently interesting
         | enough to cover in such a course.
        
       | nsxwolf wrote:
       | As someone who missed the boat on this, is learning about this
       | just for historical purposes now, or is there still relevance to
       | future employment? I just imagine the OpenAI eats everyone's
       | lunch in regards to anything AI related, am I way off base?
        
         | ksherlock wrote:
         | Maybe last week's drama should have been a left-pad moment. For
         | many things you can train your own NN and be just as good
         | without being dependent on internet access, third parties, etc.
         | Knowing how things work should give you insight into using them
         | better.
        
           | lamroger wrote:
           | I wonder if using APIs was more of a first to market move
        
           | mnky9800n wrote:
           | Which drama of last week are you referring to? The one about
           | the openai guy saying it's all just the data set? Or
           | something else?
        
       | adamnemecek wrote:
       | All machine learning is Hopf convolution, analogous to
       | renormalization. This should come as no surprise, renormalization
       | can be modeled via the Ising model which itself is closely
       | related to Hopfield networks which are recurrent networks.
        
       | dchuk wrote:
       | Hopefully not a dumb question: how do I buy a physical copy?
        
         | rossant wrote:
         | It'll be published in a few days:
         | https://mitpress.mit.edu/9780262048644/understanding-deep-le...
        
       ___________________________________________________________________
       (page generated 2023-11-26 23:00 UTC)