HNHacker News
TopNewBestAskShowJobs

maciejgryka

571 karma · joined April 23, 2009

http://maciej.gryka.net
submissionscomments
maciejgryka··on Apple to Start Publishing AI Research
I'm just at NIPS and Apple does indeed have a decent presence, which is a good sign (even if there are no actual publications yet). Super interesting to see how this will play out compared to their past. There's lots of criticism that we can throw at big tech companies, but the fact they many of them are so open about their research and thus are forcing others to do the same is pretty cool.
maciejgryka··on The Difference Between AI, Machine Learning, and Deep Learning
Only some billions of years of evolution and a lifetime of knowledge abut how our world looks like! When you see a picture of a cat your brain has a whole lot of context to put the picture into: it looks like some live creature, has eyes, legs, you can tell where it's head is, you can imagine how the fur feels like etc.

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.

maciejgryka··on Extracting image metadata at scale
It would be awesome if they released this data for another edition of the Netflix challenge, Then we could all try this ourselves!
maciejgryka··on Extracting image metadata at scale
Seam carving is cool! And there are even better methods out there - for anyone interested, this is a great starting point: http://people.csail.mit.edu/mrub/papers/retBenchmark.pdf

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.

maciejgryka··on Extracting image metadata at scale
From the code samples, it looks like OpenCV... which is pretty hard to beat for well-understood image processing algos like thresholdling etc.

I guess at this point you can do it "at scale" by throwing enough servers and caching at the problem :)

maciejgryka··on Extracting image metadata at scale
This is very interesting, but the real question is: how do you test which approach is better?

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."
maciejgryka··on Deep Learning Is Easy – Learn Something Harder
You're completely right. There's a cool quote from http://waitbutwhy.com/2015/06/how-tesla-will-change-your-lif...:

    "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.
maciejgryka··on Deep Learning Is Easy – Learn Something Harder
Now it gets much more fuzzy, but for the sake of the argument (after all why are we here? ;)) I'm willing to bet that there are lots of data science jobs that could be done well given a good knowledge of how to use deep learning and no understanding of how EM works.

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.

maciejgryka··on Deep Learning Is Easy – Learn Something Harder
That really depends on what you want to do - I bet there are still people making very decent living after learning how to make WordPress themes in 2005. Sure, you need to keep up to date and constantly learn, but you don't necessarily need to know details about how Apache works if you're just making a portfolio page.

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.

maciejgryka··on Deep Learning Is Easy – Learn Something Harder
That's a little bit like saying: don't learn web development, it's too easy, invest in learning fundamentals of computer science instead.

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.

maciejgryka··on The Unreasonable Reputation of Neural Networks
Nice article - it's good to be realistic about what we can do with current tools.

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.

maciejgryka··on Heroku for Science
I've taken a very tiny first step towards something like this for computer graphics and vision: trying to make user studies as easy as possible: http://www.imcompadre.com It's not a ready product by any means, but two paper submissions have been made with it so far.

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.

maciejgryka··on Homebrew Oculus Rift Eye Tracker
That's pretty cool! It's also possible to put the cameras below the eyes, if you're comfortable cutting through the lenses: http://arstechnica.com/gaming/2014/06/why-eye-tracking-could...

(disclaimer: I work for SMI)

maciejgryka··on Announcing Two Scoops of Django 1.6
Haven't seen this version yet, but the 1.5 edition was a great resource for me. If you've done something with Django already and are trying to improve, this book is perfect.
maciejgryka··on Poll: Full-time software engineer salaries in Berlin
That's so true. I'm lucky to have a German-speaking girlfriend and it makes a huge difference.
maciejgryka··on Poll: Full-time software engineer salaries in Berlin
I've just made the same move, feel free to get in touch if you have any more questions! I've only been here for about 3 weeks so far, so don't have much data, but €500/month for living costs seems easy.

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!

maciejgryka··on Ansible 1.3
Can't wait to try the new cloud provisioning stuff. Did anyone play with it from the dev branch and can share some experiences?
maciejgryka··on Security advisory: Breach and Django
You can still safely compress your static files. So, assuming that you don't send any secrets in your CSS, JS etc., you can configure your server to enable gzip only for these resources.

For example, when using nginx and with gzip off globally, you can do :

    location /static/ {
        gzip on;
        ...
    }
maciejgryka··on PEP 8 Modernisation
I'm not sure I'd call it controversial, but it is definitely a small annoyance because of muscle memory.

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!

maciejgryka··on PEP 8 Modernisation
Ah crap, say it ain't so. Never noticed that before (in the "Comments" section):

    "You should use two spaces after a sentence-ending period."
maciejgryka··on Schema Migrations for Django
Wow, I haven't been following Kickstarter projects as closely before, but this seems to be rising quite quickly!

I guess all the right ingredients are here: someone competent providing a useful service with an achievable goal. Nicely done and good luck!

maciejgryka··on Introducing django-db-tools - A read-only mode for your Django app
Looks really good!

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?

maciejgryka··on Pay Too Much for everything
I highly recommend The Paradox of Choice http://www.amazon.com/Paradox-Choice-Why-more-less/dp/006000...

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.

maciejgryka··on Technical Papers Every Programmer Should Read (At Least Twice)
I'd recommend the following two (both free online):

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/

maciejgryka··on Algorithms to enhance or transform images
That's right AFAIK, it's PatchMatch http://gfx.cs.princeton.edu/pubs/Barnes_2009_PAR/index.php
maciejgryka··on Who are the polite Indians?
I had the same issue. After installing reCAPTCHA (it's a WordPress blog) the problem disappeared immediately, which proves it was spam.
maciejgryka··on No Survivors in Crash of Flight Carrying Polish Leader
There's only a law (in Poland) to avoid the president and the prime minister being on the same plane. Beyond that it's not regulated.
← PreviousPage 3 of 3