Skip to content

GCRI · Zîrekiya çêkirî û pergalên xweser

Machine learning behaviour

Artificial intelligence and machine learning is the technology this platform stewards for the network. Here it is studied as a technology whose behaviour must be understood: how models learn from data, generalise, fail outside their training distribution and are adapted to specific uses.

01Qeyd

Machine learning behaviour on the record.

Method recordSTEM method
  1. RêbazZîrekiya çêkirî û fêrbûna makîneyê
  2. ParêzvanZîrekiya çêkirî û Pergal
  3. Applied inZîrekiya çêkirî û pergalên xweser
  4. Canonical pageSTEM Commons
02Application

What artificial intelligence and machine learning does here.

Artificial intelligence and machine learning develop algorithms that learn patterns from data to classify, predict or generate outputs. They are increasingly used for hazard detection, forecasting and decision support, and are themselves a source of risk. In artificial intelligence and data and compute, machine learning can scale detection and forecasting across interconnected pergalan. Its own failure modes must be weighed when automated outputs inform consequential decisions. The canonical description is on STEM Commons.

Distribution shift analysis

Model performance is compared between training data and deployment data to detect shifts in inputs or labels that reduce accuracy, with monitoring set up to catch drift.

Fine-tuning for a specific use

General models are adapted to a narrow task with curated data, and the adapted model is evaluated for both task performance and retained safety behaviour.

Interpretability methods

Feature attribution and probing methods are used to examine which inputs drive a model’s outputs, with their limits as explanations stated.

03Simulator

Modeleke sînor a tevgera kolektîf.

Her ajan dema ku têra têkiliyên wê kiriye tevdigere; guherînên piçûk di sînora navîn an di yên pêşîn de diyar dikin ka tevger herêmî dimîne an di nav nifûsê de kaskade dibe. Modela hînkirinê bi nirxên ronîker ên diyarkirî, ne pêşbînî.

Kontrol

Sînora navîn (beşa cîranan)
18%
Belavbûna sînoran
8 xal
Pêşengên tevgerê
2.0% ya mirovan
Têkilî ji bo her kesî
8

Xwendin

Beşa yên ku di dawiyê de çalakî kirin
100%
Zincîra cîhanî
Erê
Gavên çareserkirinê
10
Jimar, rêbaz û çavkanî
GavBeşa yên ku çalakî kirine (%)
02.3
16.5
216.0
328.5
447.0
565.3
680.3
793.0
899.3
9100.0
10100.0

Rêbaz

  1. Modelên sînor ên tevgera kolektîf Granovetter (1978), American Journal of Sociology 83
  2. Zincîrên cîhanî li ser torên rasthatî Watts (2002), PNAS 99
  3. Belavbûnên tevlihev Centola and Macy (2007), American Journal of Sociology 113
  4. Hesasiyeta yek-yek (tornado) Saltelli and others (2008), Global Sensitivity Analysis: The Primer, Wiley

Dane

No observed data enters this model: it runs on the teaching values set by the controls, to be replaced with a programme’s own evidence.

Modeleke sînor a tevgera kolektîf. Modeleke hînkirinê ya ronîker: li gorî nirxên ku kontrol destnîşan dikin dixebite, ne li ser daneyên pîvandî. Rêbaz: Modelên sînor ên tevgera kolektîf (Granovetter (1978), American Journal of Sociology 83); Kaskadeyên gerdûnî li ser torên rasthatî (Watts (2002), PNAS 99); Vegirtinên tevlihev (Centola û Macy (2007), American Journal of Sociology 113).
04Dane

What the method consumes.

Datasets and records used by artificial intelligence and machine learning on this platform, with the role each plays and the label its values carry. Sources are listed in the source register.

DaneRolNîşan
Training and validation datasets with documentationModel developmentDECLARED
Deployment input logsShift detectionÇAVDÊRÎKIRÎ
Benchmark suitesComparisonREPORTED
05Rêbaz û delîl

How machine learning behaviour is modelled, measured and tested.

Model, texmînên wî, daneyên wî û nediyariya wî, bi şeweyê ku zanyar an endezyar kontrol bike. Avahî rêbazên weşandî dişopînin. Nirxên hatine xêzkirin nimûneyî ne, ne encam in.

Model, hevkêşe û texmîn

The model structure used for machine learning behaviour, the assumptions it makes and how each is tested.

Xetera hêmana iRi = f(Hi, Ei, Vi, Ci)metirsî, rûbirûbûn, lawazî û kapasîteya serederiyê
Windahiya salane ya hêvîkirîEAL = ∑k pk · Lkli ser bûyerên k bi îhtîmala salane pk
Pergalên girêdayîxt+1 = A xt + B ut + εtA carries the couplings, u the shock, ε the error
TexmînÇima tê çêkirinÇawa tê ceribandin
Metirsî û rûbirûbûn di nav bûyerekê de serbixwe neEntegrala windahiyê ji hesabkirinê re maqûl dihêleBi lihevhatineke copula li ser tomarên hevbeş re bidin ber hev
Girêdan li nêzî xala xebatê xêzik inDihêle şok di A de belav bibinJi derveyî rêza xêzik tevlihev bike û bide ber hev
Xêzên lawaziyê di navbera cihan de têne veguhastinXêzikên herêmî kêm tên dîtinLi hember windahiyên çavdêrîkirî erê bike li cihê ku hene
Têketin
danehevên bi guhertoyan û çavkaniyê
Derketin
belavkirin, tu carî jimarên tenê
Kod
bi qerta modelê û ceribandinan re hat weşandin
Zêdebûn
heman dane, kod, jîngeh û tov
Formulasyonên standard ên xetereyê û qada rewşê; texmînên navborî ji bo rêbazê tîpîk in, ji bo nirxandinê hatine diyarkirin, ne encam in.
Prensîbên rêber ên FAIR · GO FAIR û FORCE11W3C PROV · World Wide Web ConsortiumRêwerzên ji bo birêvebirina hevgirtî ya nediyarîyan · IPCCCEOS Analysis Ready Data · Committee on Earth Observation Satellites
06Erêkirin

How results are checked.

Models are evaluated on held-out data that respects spatial, temporal and group structure. Robustness, calibration and fairness are tested alongside accuracy.

Kontrol bikinHow it is done
Held-out evaluationModels are evaluated on data not used for training or tuning
Dataset documentationTraining data carry datasheets on origin, consent and limits
Drift monitoringDeployed models are monitored for input and performance drift

Performance degrades when deployment conditions differ from training data. Models can encode biases and fail without clear warning on rare events.

08Stewardship

Who maintains the method.

Zîrekiya çêkirî û Pergal stewards artificial intelligence and machine learning for the Consortium and reviews how it is applied across platforms.

09Pirs

Pirs û bersiv.

What are the limits of artificial intelligence and machine learning in this field?
Performance degrades when deployment conditions differ from training data. Models can encode biases and fail without clear warning on rare events.
How are results checked?
Models are evaluated on held-out data that respects spatial, temporal and group structure. Robustness, calibration and fairness are tested alongside accuracy.
Are the values on this page real?
The data names, roles and checks are real descriptions of practice. The canvas shows a design of the method’s use, not a run; no result is reported here.
Where else is this method applied?
Çavdêrxaneya canonical method page lists every platform that applies it.
rêzeya Pergalên StratejîkTevkarî bike

Ji vê rûpelê delîl bidin.

rêzeya Pergalên Stratejîk is the Consortium’s quarterly publication. What you know about this subject can become evidence, a case or a correction in the next edition, credited to you and published under CC BY 4.0 where it is your own work.

GCRIZîrekiya çêkirî û pergalên xweserTeknolojiya eksponensiyelDelîlên Labs
Zîrekiya çêkirî û pergalên xweser

Rêbazek, danehevek an pirsek bîne.

Agahî û pirs îro vekirî ne. Pirsek referansekê distîne û gava piştî wê dide nasîn; serlêdan, drav, veqetandina hesabkirinê û tomarkirin tenê dema ku tîm, mercên wê û kapasîteya vekolînê hebin vedibin.