A non-technical explanation of deep learning
1–10 of 139 posts
Re: A non-technical explanation of deep learning
#2As someone who knows barely enough to be dangerous, I like this. I'm sure it leaves enough out to make most experts angry, but it makes a lot of sense to me.
Re: A non-technical explanation of deep learning
#3> This is how neural networks work: they see many examples and get rewarded or punished based on whether their guesses are correct.
This description more closely describes reinforcement learning, rather than gradient based optimization.
In fact, the entire metaphor of a confused individual being slapped or rewarded without understanding what's going on doesn't really make sense when considering gradient optimization because the gradient wrt the to loss function tells the network exactly how to change it's behavior to improve it's performance.
This last point is incredibly important to understand correctly since it contains one of the biggest assumptions about network behavior: that the optimal solution, or at least good enough for our concerns solution, can be found by slowing taking small steps in the right direction.
Neural networks are great at refining their beliefs but have a difficult time radically changing them. A better analogy might be trying to very slowly convince your uncle that climate change is real, and not a liberal conspiracy.
edit: it also does a poor job of explaining layers, which reads much more similar to how ensemble methods work (lots of little classifiers voting) than how deep networks work.
Re: A non-technical explanation of deep learning
#4Does this article imply there are circumstances where a spreadsheet is a cat? What a poor example of technical writing.
Re: A non-technical explanation of deep learning
#5Nothing about LLMs?!
Re: A non-technical explanation of deep learning
#6As someone who knows barely enough to be dangerous, I like this. I'm sure it leaves enough out to make most experts angry, but it makes a lot of sense to me.
> I'm sure it leaves enough out to make most experts angry
It's not that it leaves out details, it's that the articles metaphors are not actually correct in regards to the way deep learning works.
This post mostly confuses both reinforcement learning and ensemble models with deep learning. If you only enough "enough to be dangerous" then this post will steer your intuition in the wrong direction.
Re: A non-technical explanation of deep learning
#7Funny. In the game black&white you would slap or pet your avatar to train it. The lead AI programmer on that was Demis Hassabis of deepmind fame.
Re: A non-technical explanation of deep learning
#8The problem with deep learning is opposite. You can understand most of it with just high school math. Advanced math is mostly useless because of the dimensionality of neural nets.
Re: A non-technical explanation of deep learning
#9This is the funniest refutation of the Chinese Room argument that I’ve seen. Note that at the end, it’s still the case that none of these people can recognize a cat.
Re: A non-technical explanation of deep learning
#10Does this article imply there are circumstances where a spreadsheet is a cat? What a poor example of technical writing.
Not the author, but to the author's defense, it is meant to be non-technical. And the first paragraph reads interesting to me.