The complexity in twitter is that you have one channel per user, so you want to scale the "personnalized timeline". Whereas telegram/discord have clear channels.
>
This is an implementation of the "Learning Everything about Anything" system. The system
is implemented in MATLAB, with various helper functions written in Shell, Python, MEX C++
for efficiency reasons. For details about the method, please see [1].
This readme contains instructions on using the code, as well as accessing/using already
trained models for various concepts.
The software has been tested on Linux using MATLAB versions R2011a. There may be compatibility
issues with older versions of MATLAB. At least 4GB of memory (plus an additional 0.75GB for each
parallel matlab worker) is assumed.
(Disclaimer: I am not an native english speaker)
The title of the article and of the algorithm (learn everything about anything) is a bit misleading. You might believe that it learns everything, period. Actually it's more about finding every variation of a "concept", I quote their website:
"a fully automated method that given any concept, e.g., horse, discovers an exhaustive vocabulary for it that explains all variations (i.e., actions, interactions, attributes, etc) that modify its appearance."
I wonder. If they have an exhaustive vocabulary would it be possible to generate a picture of what the system believes an object to look like? I know that there is something called generative models in machine learning and my guess is that it could be applied here.
It's possible, but generally generative models have to be trained in a specific way. If not, you could do something like for every layer of the neural net, you train another NN which can "predict" the layer below it, it's input. Then you can work your way down each layer to try to find an input which would produce that output.
Another way is to use some kind of optimization to find an input which produces that pattern (e.g. backprop to the pixels themselves.) This will give you the image that most strongly triggers that output. Not necessarily a typical example.
Well you'd have to build a probabilistic model for each concepts, whether on pixels or on features, and you could use it to generate images randomly. It might show up some good shapes.
Yes, I remember that well. Seeing the animated graphics linked within that article really was an 'ah ha!' moment for me; I'd definitely recommend it as an introductory intuitive motivation.
I do agree with you speed typing might not be the most valuable skill to a programmer. Being able to type without a lot of typos is a lot more usefull since they can create hard to find bugs.
I'm puzzled, what's the use case for threads in the node asynchronous model ? Isn't the major use of threads is to prevent long running task from blocking the app in synchronous programming ?
IO is asynchronous, but code execution is not asynchronous. If a block of code is doing intensive math for 100ms, then that blocks the whole process, and potentially other IO, from executing in that 100ms.
Perhaps you should think of node as "event-driven" rather than "asynchronous".
CPU-bound loads still block the event loop. Modules take care of this behind the scenes (sometimes?) but if you're rolling your own expensive operation threads can come in handy.
