â€śMultilayer neural networks are among the most powerful models in machine learning, yet the fundamental reasons for this success defy mathematical understanding.â€ť
Source : Proceedings of the National Academy of Sciences 2018 115 (33)
'Artificial Intelligence' (AI) systems predominantly use Neural Networks to achieve their 'Machine Learning' capability. However :
No underlying principle has guided the design of these learning systems, other than vague inspiration drawn from the architecture of the brain (and no one really understands how that operates either).â€ś
Source : Quanta Magazine Sept. 2017
A theory known as the 'Information Bottleneck Method' which was first proposed in 1999, is currently being evaluated as a possible explanation - but as yet there is no general agreement on how the networks operate.
A further complication is that the 'back propagation' technique which artificial neural nets use doesn't have a direct equivalent in biological neural nets. Biological neural nets have however been shown to locally back-propagate their electrical action potentials. The function(s) of this phenomenon is also currently unexplained.
While there is ample evidence to prove the existence of backpropagating action potentials, the function of such action potentials and the extent to which they invade the most distal dendrites remains highly controversial.â€ť
Neural networks are notoriously unstable. For example, systems which have been 'trained' to recognise images, and which operate with extreme efficiency most of the time, will occasionally completely misinterpret an image and give an erroneous result. The reasons for such profound instabilities - called, in AI jargon 'Hallucinations' - are currently unknown.
Given all the above, it follows that technical systems which are strongly based around neural networks tend to work in ways which the designers don't fully understand. For an overview regarding current AI systems, particularly Large Language Models (LLMs) see Scientific American May, 2023.
Editor's note: This is a another example of a modern man-made technological system which clearly works, but that no-one as yet understands. Also see : and and
(Note there are many examples of man-made medicines which work in as-yet-unexplained ways - see the medicine / drugs section for examples.)
Ideas for new topics, and suggested additions / corrections for older ones, are always welcome.
If you have skills or interests in a particular field, and have suggestions for Wikenigma, get in touch !
Or, if you'd like to become a regular contributor . . . request a login password. Registered users can edit the entire content of the site, and also create new pages.
( The 'Notes for contributors' section in the main menu has further information and guidelines etc.)
You are currently viewing an auto-translated version of Wikenigma
Please be aware that no automatic translation engines are 100% accurate, and so the auto-translated content will very probably feature errors and omissions.
Nevertheless, Wikenigma hopes that the translated content will help to attract a wider global audience.