Humans and animals get a staggering amount of data just by wandering around their environment and interacting with things.I wonder about that too! But somehow, humans and other animals cope with that.
Nice.On the other hand:In general, there is so much we simply don't know about how biological brains work that building algorithms based on what we guess about how they work can be a road to nowhere. It's clear we need more than CNNs, not clear what exactly it is, and also not at all clear that we should replicate closely the messy result of evolution of natural selection. E.g. biological brains have a lot of redundancy in them because they have to be resistant to damage (getting whacked on the head). Artificial neural networks don't have to be.
- most of this data is not labelled
- we don't actually know how much of this data is remembered and available for more than one pass of the "learning algorithm"
- we don't know how detailed a representation is remembered
- we know that a lot of what we think we "see" is actually our brain filling in the gaps in what the eyes send to it (this is where many optical illusions come from)
- neural networks also rely on contextual information to classify objects, e.g. the presence of waves in the photo makes it more likely that a CNN will think it saw a whale in it
You also seem to engage in a circular argument in the last two paragraphs of your post, by attempting to explain the superior vision abilities of animals by referring to data which are available to them thanks to the same vision or other cognitive abilities ("get data from objects" - how do they know they see objects? how do they combine points of light into objects? how do they represent an object in their memory for further processing?). If we train our CNNs to segment bitmaps into objects and remember them, half of our work will be done
It's a very tricky subject. It's easy to fall into these traps. You should carefully define terms you're using.
That's not true: at least primates can recognise photographs. Many animals also pass the infamous "mirror test".There is much we don't know about how humans and animals learn to see. But it is clear that they fail to learn to see if only exposed to disembodied snapshots the way current AI systems are. Even streaming imagery is insufficient. Interacting with the world, moving through it, reaching out and touching things seems totally essential.
Creature only passs the mirror test after extensive training about life. Human babies, for example, can't pass the mirror test until somewhere between 13 and 24 months.That's not true: at least primates can recognise photographs. Many animals also pass the infamous "mirror test".There is much we don't know about how humans and animals learn to see. But it is clear that they fail to learn to see if only exposed to disembodied snapshots the way current AI systems are. Even streaming imagery is insufficient. Interacting with the world, moving through it, reaching out and touching things seems totally essential.
What about bats?That's not true: at least primates can recognise photographs. Many animals also pass the infamous "mirror test".There is much we don't know about how humans and animals learn to see. But it is clear that they fail to learn to see if only exposed to disembodied snapshots the way current AI systems are. Even streaming imagery is insufficient. Interacting with the world, moving through it, reaching out and touching things seems totally essential.
They wing it.What about bats?That's not true: at least primates can recognise photographs. Many animals also pass the infamous "mirror test".There is much we don't know about how humans and animals learn to see. But it is clear that they fail to learn to see if only exposed to disembodied snapshots the way current AI systems are. Even streaming imagery is insufficient. Interacting with the world, moving through it, reaching out and touching things seems totally essential.
OK, so you meant that all animals need multi-modal experience in order to develop vision. I can take it on faith, but I doubt anyone tested this experimentally (and I wouldn't want any animal to be subjected to such an experiment).Creature only passs the mirror test after extensive training about life. Human babies, for example, can't pass the mirror test until somewhere between 13 and 24 months.That's not true: at least primates can recognise photographs. Many animals also pass the infamous "mirror test".There is much we don't know about how humans and animals learn to see. But it is clear that they fail to learn to see if only exposed to disembodied snapshots the way current AI systems are. Even streaming imagery is insufficient. Interacting with the world, moving through it, reaching out and touching things seems totally essential.
What?They wing it.What about bats?That's not true: at least primates can recognise photographs. Many animals also pass the infamous "mirror test".
OK. Bats communicate by sound.
BTW, based on fMRI studies, different regions of the brain are responsible for corporal and mental identity perception (elephants, humans, chimps, dolphins and one of my cats are indeed confirmed to have the first based on the mirror test). Still, it's something different than recognising any object.OK, so you meant that all animals need multi-modal experience in order to develop vision. I can take it on faith, but I doubt anyone tested this experimentally (and I wouldn't want any animal to be subjected to such an experiment).Creature only passs the mirror test after extensive training about life. Human babies, for example, can't pass the mirror test until somewhere between 13 and 24 months.That's not true: at least primates can recognise photographs. Many animals also pass the infamous "mirror test".
There's a long line of such research but you and kata would be truly appalled by it. Perhaps the most interesting one (http://marom.net.technion.ac.il/files/2 ... d-1963.pdf) gave two kittens identical visual experiences but only one kitten of the pair got to explore its environment. The kitten that only saw the world passively never developed binocular vision as judged by failing the blink test, visual cliff test, and paw-eye coordination test. Because the one kitten never got to explore on its own, it never learned near and far (which would seem to require experiencing self-propelled motion toward and away from things) or that visual data gave any indication of distance.OK, so you meant that all animals need multi-modal experience in order to develop vision. I can take it on faith, but I doubt anyone tested this experimentally (and I wouldn't want any animal to be subjected to such an experiment).Creature only passs the mirror test after extensive training about life. Human babies, for example, can't pass the mirror test until somewhere between 13 and 24 months.That's not true: at least primates can recognise photographs. Many animals also pass the infamous "mirror test".