…ather than neurons but building the same sorts of complex interconnections between them (synapses). Rather than storing all data in a huge pool to be analyzed as a whole, neural networks are able to memorize and so remember associations between concepts, streamlining the process of retrieval and analysis.
Cristian Randieri, Phd
Artificial neural networks do do not remember or memorize anything. They are not capable of the act of memorization or remembrance nor can they make “associations between concepts.” Only a human being with a (mostly) functional biological neural network (brain/brain stem and nervous system) and some or perhaps most non human animals are capable of remembering and memorization. Associations between concepts is a trickier topic and it is not clear that non human animals are capable of this. However, it should be beyond dispute that artificial neural networks are not.
Lest you thing I am only being biased against the “artificial” it is also true that a biological neural network, brain, nervous system, brain stem or any combination of those is/are also incapable of memorization or or remembering. Only of a whole, intact person, and possibly some or most non human animals (maybe though I doubt some insects) can we say that they have memorized something or have remembered something. To say otherwise is to commit the mereological fallacy. Attributing characteristics/traits to a part of a thing that logically can only be attributed to the thing as a whole.
To say an artificial neural network remembers or memorizes or associates between concepts is false on two levels: being non alive it is incapable of those things and being only a part of a potential whole it is a mereological fallacy. Patently false and logically impossible. The dreaded double whammy of absurdity.
And how exactly is deep learning any different than regular learning? Neither of which a machine is capable of by the way. Other than it being trendy to use words like “deep learning” and “social networks” in the same sentence is their an actual purpose behind calling something deep learning when it is just learning? It is a moot point for purposes of this piece since no learning is occurring at all deep or otherwise but I really hate that trendy hype word shit when used for no reason other than to be trendy or generate attention or clicks.
You still going to recommend every single damn thing I write literally two seconds post publishing after reading this? Kudos if you do. Unfortunately I cannot return the favor. Perhaps someday if I ever teach a course in logic and need a good example of the use of fallacious arguments and specious reasoning for my students I shall. Until that day the recommends will have to be one way only. That said you may be one hell of a sci-fi writer and just have not found your true calling yet. If that’s the case I may one day be your biggest fan just as you seem to be mine currently.