81–90 of 99 posts
Earlier quoted context omitted.
Interesting It seems it can't really handle context, so 'cockroaches' may have been a mistranslation of 'cheap' in some contexts, as the 'it had stopped chestnut' may have simply been 'brazil nuts'
Most probably the OCR read "batata" (potato) as "barata" (cockroach).
I am 15 years into this computers thing and this blog post made me feel like "those guys are doing black magic". Neural networks and deep learning are truly awesome technologies.
Two remarks. First, these guys probably don't know very well why what they are doing works so well ;) It requires a lot of trial and error, and a lot of patience and a lot of compute power (the latter being the reason why we are seeing breakthroughs only now).
Second, training a neural net requires different computing power from deploying the net. The neural network that is installed on your phone has been trained using a lot of time and/or a very large cluster. Your phone is merely "running" the network, and this requires much less compute power.
Earlier quoted context omitted.
It's not really that deep, imo: a typical deep net these days has O(10^8) parameters (e.g. http://stackoverflow.com/questions/28232235/how-to-calculate... ). You can store a hell of a lot of patterns in that many parameters, making them the best pattern matchers the world has ever seen. (Un)fortunately, pattern matching != intelligence. More interesting deep questions for which there is precious little theory revolve…
Is "pattern matching != intelligence" what occurred when the Google image recognition stuff in the news recently was shown to recognize the pattern of a "dumbbell" as always having a large muscular arm attached to it? Seemed like a great way to highlight the limitations of patterns.
This is great. I particularly like that they also automatically generated dirty versions for their training set, because that's exactly what I ended up doing for my dissertation project (a computer vision system [1] that automatically referees Scrabble boards). I also used dictionary analysis and the classifier's own confusion matrix to boost its accuracy. If you're also interested in real time OCR like this, I did a…
Earlier quoted context omitted.
You could say very much the same about the brain... > [...] the "black magic" part comes mostly from their mathematical nature and very little from them being "inteligent computers". A brain is a graph, in which a subset of neurons are "inputs", some are outputs, and others are "hidden". The nodes are interconnected between each other in a fashion, which is called the "topology" or sometimes "architecture" of the net…
If there is magic to be found, it may be in that question. Why about graphs (namely the subset that are deep neural networks) allow them to not only contain such powerful heuristics, but also allow them to be created from scratch with barely any knowledge of the problem domain. As a side note, I was playing a board game last night (Terra Mystica I believe) and wondering if you could get 5 different neural networks to…
There was in fact a group within Google that worked on this: http://www.cs.toronto.edu/~cmaddis/pubs/deepgo.pdf
[1] https://github.com/mateogianolio/mlp-character-recognition
[2] https://github.com/mateogianolio/mlp-character-recognition/b...
This is great. I particularly like that they also automatically generated dirty versions for their training set, because that's exactly what I ended up doing for my dissertation project (a computer vision system [1] that automatically referees Scrabble boards). I also used dictionary analysis and the classifier's own confusion matrix to boost its accuracy. If you're also interested in real time OCR like this, I did a…
Earlier quoted context omitted.
You could say very much the same about the brain... > [...] the "black magic" part comes mostly from their mathematical nature and very little from them being "inteligent computers". A brain is a graph, in which a subset of neurons are "inputs", some are outputs, and others are "hidden". The nodes are interconnected between each other in a fashion, which is called the "topology" or sometimes "architecture" of the net…
They are effective because: - They use more parameters (and fewer computations per parameter.) - They are hierarchical (convolutions are apparently useful at different levels of abstraction of data). - They are distributed (word2vec, thought-vectors). Not restricted to a small set of artificial classes such as parts-of-speech or parts of visual objects. - They are recurrent (RNN). etc.
This is great. I particularly like that they also automatically generated dirty versions for their training set, because that's exactly what I ended up doing for my dissertation project (a computer vision system [1] that automatically referees Scrabble boards). I also used dictionary analysis and the classifier's own confusion matrix to boost its accuracy. If you're also interested in real time OCR like this, I did a…
Funny, just read an article today proposing the same feature detection algorithm (the one you called 'grid merge'). Have you tried applying these techniques on scanned/photographed documents?
I've not tried it on anything else, but I remember thinking that it has a lot of potential uses. Also I only used it on gray-scale features, but I'm sure it could make use of full RGB too. I'll have to try it some time!
Earlier quoted context omitted.
Funny, just read an article today proposing the same feature detection algorithm (the one you called 'grid merge'). Have you tried applying these techniques on scanned/photographed documents?
Could you link to it please? I've not tried it on anything else, but I remember thinking that it has a lot of potential uses. Also I only used it on gray-scale features, but I'm sure it could make use of full RGB too. I'll have to try it some time!
http://www.eecs.berkeley.edu/Pubs/TechRpts/2009/EECS-2009-15...