Become a fan of Slashdot on Facebook


Forgot your password?

Slashdot videos: Now with more Slashdot!

  • View

  • Discuss

  • Share

We've improved Slashdot's video section; now you can view our video interviews, product close-ups and site visits with all the usual Slashdot options to comment, share, etc. No more walled garden! It's a work in progress -- we hope you'll check it out (Learn more about the recent updates).


Comment: Re:I get it (Score 1) 22

I get it, 'relatively novel'. So novel that we've been doing it for several decades and it has been used by everything from the atomic weapons program and space program to teaching Samsung how to eavesdrop on our living room conversations.

From TFA:

“This is the first time that we’re introducing probabilistic programming in the vision area,” says Tejas Kulkarni, an MIT graduate student in brain and cognitive sciences and first author on the new paper. “The whole hope is to write very flexible models, both generative and discriminative models, as short probabilistic code, and then not do anything else. General-purpose inference schemes solve the problems.”

Computer Vision research has been behind other AI areas in its use of generalisable code, but current AI and machine learning algorithms are effective and efficient enough that image processing with them is finally practical. That's the novelty.

Comment: Re:Line Count is Misleading (Score 1) 22

Yeah, sounds like they've essentially developed a library that the programming language is dependent on.

Even if you wrote wrappers to access all their libraries in (for example) Python, operating an inference engine and manipulating the results returned would be a complete pain. This is a high-level language designed as a problem-solver over a probabilistic domain. That in itself is a very far-removed abstraction from the processor's opcodes...

Comment: Re:Line Count is Misleading (Score 1) 22

"...the researchers were able to cut thousands of lines of code in one image recognition program down to fewer than 50."

How many lines of code were used to write the MIT Picture language? The article summary claims to have replaced thousands of lines of code in an existing application yet do not mention the line count of the Picture language.

Your problem is that you're thinking to heavily in terms of C-like imperative programming. Picture sounds more comparable to Prolog to me -- an automated problem-solver. The core of Picture is an "inference engine" -- the core of Prolog is an inference engine too. The difference is that Prolog operates in pure predicate logic, whether Picture is a probabilistic language.

Probabilistic programming in even a relatively high-level C-like (eg Python) would be a total pain, because you have to explicitly call all calculations. An inference engine will do the calculations implicitly and will prune any unsuccessful branches off your search tree without you having to worry about it. The end result is very complete solutions to problems with a low bug count, but (in general) relatively high execution times.

This sort of very-high-level language isn't suitable for every task, but it serves its task exceptionally well.

Comment: Re:Race but not Gender? (Score 0) 147

but must NEVER exhibit collective pride in the achievements of their ancestors(that's racism!). It's a deliberate effort to dumb them down and impair their learning ability and achievement to achieve "equality".

So you're saying that schools never celebrate the founding fathers, or Abe Lincoln, or the winning of various wars by white-led armies?

As long as Thanksgiving is celebrated (a feast to mark the massacre of a bunch of native Americans), your whining sounds like bullshit.

Comment: Re:Apartheid Education (Score 1) 147

Yeah right, race consciousness never existed in non-capitalist economies. I recall reading about an isolated tribe whose name for themselves basically meant "human" and whose name for other people who didn't look like them (like white anthropologists) meant "non-human."

This is quite a common pattern. But in these societies, the number of "humans" is limited by Dunbar's number. Renaissance racism expands the pool of identified "humans" into the millions, and post-Renaissance racism pushes into the thousands of millions and billions, and it draws the boundary in an arbitrary way. Some Indo-Europeans are dismissed as "not white", and some non-Indo-Europeans are allowed into the privileged club because of a lighter pigmentation than others. Modern racism isn't the same as natural pack mentality.

Comment: Re:ok.. so lets (Score 1) 147

In Scotland, segregation of the children of Scottish and immigrant communities (Irish, Italian, Polish) was done for a combination of right and wrong reasons. Partly it was the established elite not wanting their kids mixing with the funny foreigners, but it also did protect the poor immigrants from inherited xenophobia in the local families. The surface detail of the segregation was the mainstream (effectively protestant) schools and the catholic schools. Over the generations, the need for this system has burnt itself out. The mainstream schools have mostly become genuinely non-denominational, and most of the children of both sides have left their religions. Which country handled segregation better, Scotland or the US? I do not know. But I don't believe now is a time for increasing segregation. But that's not the point of diversity in education. The point is that all kids need to see that education is relevant to them. A poor kid from a minority slum the majority of whose adult role models are all of the same minority and are either unemployed or criminal is not going to be swayed by a clean-cut WASP sitting in front of them and telling them that they can be whatever they want.

Comment: Re:You are so right ! (Score 0) 147

I came from China. Back in China all my teachers are Chinese - as China is full of Chinese naturally my teachers (good and bad) are Chinese

But when I landed on US of A none of my teachers / lecturers / professors (good and bad) happened to be ethnic Chinese

Feeling like a foreigner in a foreign country is not a problem. Feeling like a foreigner in your own country is a problem. It alienates and results in low achievement.

fortune: cannot execute. Out of cookies.