Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Suddenly, a leopard print sofa appears

rocknrollnerd.github.io

Post reply on HN
Print view View original

21–30 of 114 posts

Re: Suddenly, a leopard print sofa appears

#21

Post by rcfox »

I don't work with NN at all, but it kind of seems like the author set up their CNN with a large enough filter to see a whole spot at once, but not large enough to see a whole cat at once. Then he complains that it doesn't know what a cat looks like. Would it be possible to make a larger filter with a lower resolution such that overhead is the same as the smaller filter but it can get a higher-level view of the image?

Also, the author spends the first section of the article determining that it is in fact a jaguar-print sofa (which the model also confirms) but continues to throw around the word "leopard". They're not making it any easier for the future machine learning algorithms that try to identify an image by the text surrounding it. ;)

Re: Suddenly, a leopard print sofa appears

#22

Post by revelation »

fla wrote: post #3

Somehow tangent but this made me think about this quote found on HN last year: Context: Evolutionary algorithms and analog electronic circuits > One thing stands out when you try playing with evolutionary systems. Evolution is _really_ good at gaming the system. Unless you are very careful at specifying all of the constraints that you care about you can end up with a solution that is very clever but not quite what yo…

You don't even need a neural net for that, take any global optimization method and give it a somewhat ill-defined scoring function, it will instantly run circles around you laughing.

Re: Suddenly, a leopard print sofa appears

#23

Post by discardorama »

yellowbkpk wrote: post #19

Let's say I didn't want to use the ImageNet or CaffeNet pre-trained models but wanted to train my own model (say, of thousands of images of sofas, leopards, jaguars, and cheetahs); are there any tutorials that walk through the process of building a CNN on your own data? (I've seen the comments like https://news.ycombinator.com/item?id=9584325 and watched the lectures and youtube walkthroughs, but they're all theoreti…

For doing image training, Caffe is pretty good. Here's a starting point: http://caffe.berkeleyvision.org/tutorial/

Re: Suddenly, a leopard print sofa appears

#24

Post by discardorama »

jng wrote: post #4

I'm happy somebody tries to put some sense into the whole absurdly overblown machine learning field.

I wouldn't call it overblown. It has been applied very successfully in a few places; for example, voice recognition.

Right now we're at the stage of the "seven blind men and the elephant". Over time, our eyes will open and things will start making sense.

Re: Suddenly, a leopard print sofa appears

#25

Post by ghaff »

discardorama wrote: post #24
jng wrote: post #4

I'm happy somebody tries to put some sense into the whole absurdly overblown machine learning field.

I wouldn't call it overblown. It has been applied very successfully in a few places; for example, voice recognition. Right now we're at the stage of the "seven blind men and the elephant". Over time, our eyes will open and things will start making sense.

Voice recognition has gotten a lot better. I'm almost impressed by my Amazon Echo. That said, for an arbitrary recording of say a conference presentation, you need to either use a human transcriber or expect to spend a LOT of time cleaning things up.

(A lot probably has to do with switching to more data-based approaches.)

Re: Suddenly, a leopard print sofa appears

#26

Post by xyproto »

https://www.imageidentify.com/ correctly identified the images as "a small sofa". I think rotating the image is questionable, since there could be an algorithm for first orienting the image correctly based on light and shadow and then the image recognition could be run.

https://www.imageidentify.com/result/1ixb9603m9ix1

Re: Suddenly, a leopard print sofa appears

#28

Post by deelowe »

jng wrote: post #4

I'm happy somebody tries to put some sense into the whole absurdly overblown machine learning field.

It's not overblown anymore than "cloud computing" is overblown. Misreported, maybe, but there is a huge shift happening in the industry right now.

If not, why else would this exist http://www.nvidia.com/object/tesla-supercomputing-solutions....?

Re: Suddenly, a leopard print sofa appears

#30

Post by quasiresearcher »

xyproto wrote: post #26

https://www.imageidentify.com/ correctly identified the images as "a small sofa". I think rotating the image is questionable, since there could be an algorithm for first orienting the image correctly based on light and shadow and then the image recognition could be run. https://www.imageidentify.com/result/1ixb9603m9ix1

But those algorithms would be very limited in usefulness. Systems such as imageidentify.com should be at least trying an ensemble of algorithms, many of which I suppose should be invariant under translation and rotation.

Edit: There's a comment about invariance in this thread [1] and apparently CNNs are not invariant under rotation.

[1] https://news.ycombinator.com/item?id=9750133

Post reply on HN