Biomimicry Intelligent Design

At Mind Matters News: One way human vision is better than a machine’s

Spread the love

The problem machine vision has with understanding what things should look like creates risks for traffic video safety systems, researchers say. “Frankensteins” — models of life forms that are distorted in some way — help researchers test the limits of machine vision for safety-related tasks.

The fact that humans and other life forms “want” things may underlie the superiority of natural vision systems to machine vision systems. It will be interesting to see how easy the gap is to close — if it can be done at all.

You may also wish to read: Researchers: Deep Learning vision is very different from human vision. Mistaking a teapot shape for a golf ball, due to surface features, is one striking example from a recent open-access paper. The networks did “a poor job of identifying such items as a butterfly, an airplane and a banana,” according to the researchers. The explanation they propose is that “Humans see the entire object, while the artificial intelligence networks identify fragments of the object.” Also: Mis-seeing can include mistaking a schoolbus for a snowplow.

12 Replies to “At Mind Matters News: One way human vision is better than a machine’s

  1. 1
    martin_r says:

    and another example the human engineering is a child play compared to God’s work … (see my other post on smellicopter https://uncommondescent.com/biomimicry/at-mind-matters-news-machine-uses-live-hawk-moth-antenna-for-smell-detection/)

    Darwinism is a scam …

  2. 2
    AaronS1978 says:

    @ Martin_r
    Yeah but the recurrent laryngeal nerve is obviously poor design and therefore no god or designer could possibly exist because the one in a giraffe is ridiculously long. Because of this I want, no demand, you believe that everything came together about by sheer chance and all of those amazing things we can’t replicate due to all of their complexity and the things they end up doing on their own, all arose by accident. That makes much more sense. Now if you’ll excuse me I’m gonna go roll a billion dice until they fall into an exact replica of the Taj Mahal

  3. 3
    martin_r says:

    AaronS1978

    laryngeal nerve … the one in a giraffe is ridiculously long. Because of this I want, no demand, you believe that everything came together about by sheer chance ….. and all of those amazing things we can’t replicate due to all of their complexity

    Exactly… Because they found one or two very very questionable design flaws, they want you to ignore millions if not billions of examples of a very sophisticated design/engineering. It is like in some mental hospital …

    According to Darwinists, at this moment, there are about 10,000,000 of kinds of species on this planet. So let’s say, each species is made of 1000 parts working in concert for a purpose.
    10,000,000 x 1000 = 10,000,000,000 parts in total.
    How many design flaws did Darwinian biologists find ?

    1 ? 5? 10 ?

    out of 10,000,000,000 working parts ?

    Once again, 10,000,000,000 parts have been working flawlessly for thousands of year (if not millions of years) … and these geniuses found one or two design flaws ?? how absurd ….

    So it clear, that this very very very rare examples of bad design, the giraffe’s long l. nerve, IS JUST ANOTHER DARWINIAN MISINTERPRETATION of a very advanced engineering – because biologists never made anything, and don’t understand engineering (let alone biology’s advanced engineering)

    One more note regarding giraffe’s long l. nerve:

    When installing an air conditioner, the outdoor unit is connected to the indoor unit with pipes of a minimal length of 2 meters (6.5 feet). It can’t be less than 2 meters, because it wouldn’t work properly. It has to be 2 meters even if the distance between outdoor and indoor unit is much less. Usually, if the distance between outdoor-indoor unit is very small, the technician makes a 2 meter-loop of pipes which is hidden behind the outdoor unit (mounted on the wall), so nobody cares, you can’t see the pipes.

    I was wondering, how would a Darwinian biologist comment on these seemingly unnecessary long pipes ?

  4. 4
    relatd says:

    Machine vision requires a human brain to effectively identify shapes. The alternative would be programming in every known shape in 3-D. But that would tax any system and fall into the “it’s too expensive category.” Machine vision can be used in very specific situations but it does not have a human brain to learn about objects it is not familiar with.

  5. 5
    Lieutenant Commander Data says:

    Exactly… Because they found one or two very very questionable design flaws, they want you to ignore millions if not billions of examples of a very sophisticated design/engineering. It is like in some mental hospital …

    I guess darwinists got it wrong even with this one:
    https://answersingenesis.org/human-body/strategic-routing-rln/

  6. 6
    doubter says:

    It turns out that the claim about the bad design of the recurrent laryngeal nerve of the giraffe falls apart upon close examination. This was discovered by Wolf-Ekkehard Lönnig.

    From an article covering this topic by Casey Luskin in http://www.ideacenter.org/cont.....hp/id/1507 :

    It seems quite likely that there are mutational pathways to a more efficient route for the RLN. Under neo-Darwinian thinking, this implies (a more efficient pathway) should have evolved. At the very least, it shows that there are no in-principle constraints based upon our alleged fish-ancestry which prevent this route from evolving. The fact that the existing pathway remains–under evolutionary logic–that there’s some benefit to the current design, which implies that the current design isn’t so imperfect after all.
    …………………….
    (Actually,)…the RLN’s sole purpose, or as ID-critic Kelly Smith put it, its “intended function,” is not simply to innervate the larynx, as it provides innervations for the heart and even for the esophagus. And for those organs it takes a direct, or as Coyne might put it, “rational” route from the brain.
    …………………….
    To innervate the esophagus and trachea of the giraffe and also reach its heart, the recurrent laryngeal nerve needs to be, indeed, very long. The Nervus laryngeus recurrens innervates not only the larynx, but also the esophagus and the trachea and moreover “gives several cardiac filaments to the deep part of the cardiac plexus” etc.

  7. 7
    Querius says:

    The flaw here is the assumption that something we don’t understand is a “design flaw.”

    I think it’s far more likely given the genius of the rest of nature, what we might consider to be a flaw does have a purpose. Otherwise, were back to the reasoning that produced the conclusions of so-called “vestigial” organs and “junk” DNA.

    -Q

  8. 8
    OldArmy94 says:

    The “argument” of bad design is a double-edged sword. If Darwinian evolution was half as clever as its proponents claim it is, with all of its convergent and divergent evolutionary schemes, then it would have long ago eliminated any such alleged flaws.

  9. 9
    asauber says:

    Alan Fox will tell you how horrible The Niche is at designing things.

    Andrew

  10. 10
    relatd says:

    OA94 at 8,

    Cries of ‘bad design’ is just a cry of frustration. Might as well cancel the Olympics since human bodies are so badly designed. The same with figure skating. It can’t be done.

  11. 11
    relatd says:

    Andrew at 9,

    The Niche is a magical invention that can guide and smooth off the rough edges of living things, like a lathe. Oh yes, something with no brain and no goals just “knew” The Niche would give it a hand.

  12. 12
    asauber says:

    Relatd,

    Yes Alan Fox thinks if you give The Niche a lump of clay, you’ll eventually have to contend with a Pterodactyl. Or The Borg.

    Andrew

Leave a Reply