571 karma · joined April 23, 2009
An untrained neural net has to learn everything from scratch (ha!), from pixel values to "knowing" what a cat is. There is some work on decreasing the amount of data needed to learn, but it's a very tricky subject.
All of these methods have advantages, but it's pretty hard to out-weight the simplicity of cropping, especially if you're sensitive to bad results.
I guess at this point you can do it "at scale" by throwing enough servers and caching at the problem :)
For example, in the text detection case there are almost unlimited combinations of transforms that you can put together. Usually you use some hybrid of gut feeling and results to decide, but I bet Netflix has enough data to make that call in a more principled way.
Would be awesome to hear about that. How do you create a labeled dataset? How exactly do you measure which approach is better? Is there a perceptual element to it, or is it all quantitative?
Edit: here's the related money quote from the retargeting paper linked in the other comment:
"In terms of objective measures for retargeting, our results show that we are still a long way from imitating human perception. There is a relatively large discrepancy between such measures and the subjective data we collected, and in fact, the most preferred algorithm by human viewers, SV, received low ranking by almost all automatic distance measures." "I’ve heard people compare knowledge of a topic to a tree. If you don’t fully get it, it’s like a tree in your head with no trunk—and without a trunk, when you learn something new about the topic—a new branch or leaf of the tree—there’s nothing for it to hang onto, so it just falls away. By clearing out fog all the way to the bottom, I build a tree trunk in my head, and from then on, all new information can hold on, which makes that topic forever more interesting and productive to learn about. And what I usually find is that so many of the topics I’ve pegged as “boring” in my head are actually just foggy to me—like watching episode 17 of a great show, which would be boring if you didn’t have the tree trunk of the back story and characters in place."
I think learning to use APIs is probably the way to start, but it definitely pays off to keep digging deeper as you go along.I'm not saying that knowing fundamental (and/or difficult) topics is not useful - it absolutely is! It's just a matter of prioritizing what you learn about. I think if you want to maximize your impact, it makes sense to invest in learning the currently-most-promising tool before going for things with lower reward/effort ratio.
I don't want to discourage anyone from learning hard topics - it can be very rewarding and useful. I just object to the sentiment that learning how to use a tool has no value if you don't have an intimate understanding of it. It still gives you the power to solve new problems.
Sure, if you want to innovate in the field of academic AI, you probably need to know much more than how to throw some data at a neural net. But there are SO MANY problems supervised learning can solve out there - much like there are so many people and businesses who need a website done.
It's a tool, like any other - and right now it seems very hard to beat. So please go ahead, learn how to use it, and apply it to your own problem domain.
I feel like the gist of what current neural nets can do is "pattern recognition". If that's fair, I also suspect that most people underestimate how many problems can be solved by them (e.g. planning and experiment design can be posed as pattern recognition - the difficulty is obtaining enough training data).
It's true that we're most likely a very long way away from general AI - but I'm willing to bet most of us will still be surprised within the next 2 years by just how well some deep-learning based solutions work.
It's a difficult problem to solve, because these pesky researchers are always trying out new things that you didn't anticipate - who would've thought! But still, for the mundane things that can be automated, something like this is definitely the way to go. Of course, as other people here point out, figuring out what to actually test is always the hardest part.
(disclaimer: I work for SMI)
Rent, depending on what you want, is probably about 80% of what you pay for a comparable flat in London. You can probably get 2 bedrooms (+living room) with all the bills included for about €800. Just be prepared for seriously unfurnished flats: sometimes you need to get your own kitchen! Also it apparently takes a lot more time and paperwork than in London to find something - people say 3-4 months is normal and I'm still looking.
Good luck!
For example, when using nginx and with gzip off globally, you can do :
location /static/ {
gzip on;
...
}Anyway, in the grand scheme of things this is really insignificant :) The fact that PEP8 exists at all is just one of the things making Python great!
"You should use two spaces after a sentence-ending period."I guess all the right ingredients are here: someone competent providing a useful service with an achievable goal. Nicely done and good luck!
Just a thought - when using the GET_ONLY_MODE you should probably be careful with your sessions if you're storing them in your database right?
To quote from the article: "People who constantly try to always get that great deal end up spending all their time chasing those deals and never actually get things done. I’ve seen people do this their entire lives, and it is debilitating."
You can say the same about people who spend all their time trying to constantly get "the best" product. Figure out a few things that are important to you and maximise these - whether on quality or price. For the rest, learn to accept "good enough" and get on with your life doing things that matter for you.
The Elements of Statistical Learning: http://www-stat.stanford.edu/~tibs/ElemStatLearn/
Second, while focused on computer vision, has great intro to probability and learning:
Computer Vision: Models, Learning, and Inference http://computervisionmodels.com/