Yes, I’ve completed that course.
May I take issue with your comment “AI might really distinguish between two real species but it won’t be able to tell you how it has distinghished them”? Surely this is simply a feature of the particular implementation of the AI? It would be possible (perhaps even easy) for the system to provide a record of it’s decision-making process even if “fuzzy logic” techniques are used. If an AI system can’t do this I would doubt very much if it can be trusted; it may be, of course, that this isn’t implemented in the public-facing version but only in versions subjected to appropriate peer review.
Rule based expert systems can tell you why they’ve come to particular conclusions. If I understand correctly neural net based systems can’t - their behaviour is an emergent property of a set of weights. For example AlphaZero can beat the best human players at Go, Chess and Shogi. It does this by having taught itself a better algorithm for evaluating board positions.
Even human experts can always tell you why they came to the conclusion that they did.
The next milestone for AI might be protein folding.
One technique used to identify morphologically distinctive units is principal comments analysis. An AI might end up doing something equivalent - using correlations of characters to identify units. For example, given a sufficiently large sample of DNA identified specimens of Sonchus asper and Sonchus oleraceus it might be able to identify the ambiguous specimens with superhuman accuracy and even identify the hybrids. But some degree of caution is necessary - the accuracy depends on the training set. For example a AI trained on British Leontodon may not work when exposed to specimens from the continent.
As a person who’s not keen on morphological species concepts I don’t think that an AI can divide a set of individuals into species from first principles - on the one hand morphs, castes, sexual dimorphism, metamorphosis could result in false positives, and cryptic species in false negatives.
Exactly! There is an algorithm - a (self-)developing algorithm but an algorithm nevertheless. The system should therefore be able to describe both the methods it is applying (the algorithm) and the methods it uses to modify the algorithm.
But humans won’t be able to understand the particular bit (part of the database it has created plus code) that distinguishes the particular species. Getting the computer to explain this somehow might be a next stage.
The humans developed the ai then let it run but the last part is still missing, getting the computer to tell and explain exactly what it has used to separate the species. This is a general issue with ai doing this type of task, it is not unique to species identification.
Am sure there will be much more on this over the next couple of years.
Another example from PlantNet Identify. (The first two offers were at least in the right order - and nearly led me astray be confirming my initial guess - but it then went into the weeds, but the low probability scores.)
There been a recent batch of confidently identified obscure plants from gardens. I’d added tentative corrections to some of them, but while using PlantNet Identify to remind myself of the name of Desfontainia spinosa (given by the observer as Brugmansia sanguinea) I acquired the suspicion that the identifications had come from PlantNet Identify or a similar app in the hands of a user not au fait with its limitations.
(But having tried some of his other images in PlantNet Identify it would seem that he’s not using that in particular.)
That is interesting. Some time ago I used Plantnet to ID something and noticed that some of the other species associted with the identification on Plantnet were wrong (they give a bunch of other images to look at for the ID). Perhaps words to indicate that no system, humans or AI are right all the time but everyone should strive to be as accurate as is possible perhaps by using multiple methods of identification.
iForum LIVE! session: Cos4Cloud services - Why are we integrating FASTCAT-Cloud and the Plantnet API into iSpot?
We have been trialling the integration of two Cos4Cloud image recognition technologies FASTCAT-Cloud and the Pl@ntnet-API on iSpot since June 2022. Want to know more about Why we are integrating FASTCAT-Cloud and the Pl@ntnet API into iSpot? you are invited to join a iForum LIVE! scheduled chat discussion in the iSpot Forum on Thursday August 4th at 3 – 4 pm BST / 4 – 5 pm CEST. Click on this link to participate: iForum LIVE!: Why are we integrating FASTCAT-Cloud and the Plantnet API into iSpot?
Please note you will be invited to join the iSpot Cos4Cloud User Group to participate. We are keen to share and gather the iSpot community’s feedback and have users involved in testing and this iFORUM LIVE! discussion is part of this. See more: About the Cos4Cloud Project: iSpot Cos4Cloud User Group
Dear all
Please join us for the Cos4Cloud iSpot User Group2nd iForum LIVE! . The focus of this session is: AI and iSpot: a spotlight on the Pl@ntNet API.
This LIVE scheduled chat discussion with the Pl@ntNet API development Team and iSpot Admin will be on Wednesday, October 12th 5:30 p.m. BST / 6:30 p.m. CEST at this link.
