OER·harvester

Competency catalogue

The 104 active T2.3 competencies: the vocabulary the harvester searches with, the descriptor the alignment reads, and what the alignment found. Compose a harvest →

What the alignment foundHow often each was searched

How many resources the alignment reads as contributing to each competency or developing it: decided at level 2 or 3, or not decided yet and more likely than not to reach 2. 54 competencies have none, 24 one or two. Every figure is a lower bound: on a sample graded on every competency, the map counts 33% of what was graded 2 or 3, and almost nothing of the 5 competencies underlined with dots.

How many times a harvest has searched for each competency, once for each source it asked. 101 competencies have never been searched. A search is not material found: the aligned view says what came of it.

none 1–2 3–9 10–29 30+
never 1–2 3–5 6–11 12+
DDigital 94212203420012149086012303134 GGreen 0000000102000010000100010 RResilience & Entrepreneurial 004000000000000010000120000 TDeep Tech 72643202372825212335201140010

T01 Deep Tech · Knowledge · Foundation

Neural Network Architecture

Understand structure of neural networks and deep learning

Alignment

7 resources likely to contribute to it or develop it

0 decided at level 2 or 3 · 7 not decided yet, more likely than not

On a graded sample, 9 pairs were graded 2 or 3 for it, and the map counts 3.

Retrieval

0 resources harvested by searching its terms

Never searched yet.

Search vocabulary

Domain group
neural network architectureneural network layersneural netsactivation functionbackpropagationconvolutional networkrecurrent networkdeep neural networktransformer modelmixture of expertsMoEmodel parametersweight matrix

Zenodo and arXiv take the whole group in one query. GitHub takes one phrase at a time and works left to right, stopping once the competency is satisfied — so on that lane this order decides which terms actually run.

The compiled queries
zenodo ("artificial intelligence" OR "machine learning" OR "generative AI" OR "deep learning" OR "reinforcement learning" OR "large language model" OR "AI") AND ("neural network architecture" OR "neural network layers" OR "neural nets" OR "activation function" OR "backpropagation" OR "convolutional network" OR "recurrent network" OR "deep neural network" OR "transformer model" OR "mixture of experts" OR "MoE" OR "model parameters" OR "weight matrix")
arxiv (all:"artificial intelligence" OR all:"machine learning" OR all:"generative AI" OR all:"deep learning" OR all:"reinforcement learning" OR all:"large language model") AND (all:"neural network architecture" OR all:"neural network layers" OR all:"neural nets" OR all:"activation function" OR all:"backpropagation" OR all:"convolutional network" OR all:"recurrent network" OR all:"deep neural network" OR all:"transformer model" OR all:"mixture of experts" OR all:"MoE" OR all:"model parameters" OR all:"weight matrix")
github · term 1 AI "neural network architecture" in:name,description,readme fork:false archived:false
github · term 2 AI "neural network layers" in:name,description,readme fork:false archived:false
github · term 3 AI "neural nets" in:name,description,readme fork:false archived:false
github · term 4 AI "activation function" in:name,description,readme fork:false archived:false
github · term 5 AI "backpropagation" in:name,description,readme fork:false archived:false
github · term 6 AI "convolutional network" in:name,description,readme fork:false archived:false
github · term 7 AI "recurrent network" in:name,description,readme fork:false archived:false
github · term 8 AI "deep neural network" in:name,description,readme fork:false archived:false
github · term 9 AI "transformer model" in:name,description,readme fork:false archived:false
github · term 10 AI "mixture of experts" in:name,description,readme fork:false archived:false
github · term 11 AI "MoE" in:name,description,readme fork:false archived:false
github · term 12 AI "model parameters" in:name,description,readme fork:false archived:false
github · term 13 AI "weight matrix" in:name,description,readme fork:false archived:false

Profile 5480b268be632d14

Alignment descriptor draft

Outcomes
  • Can explain neurons, layers, weights, activation functions and how a network computes an output.
  • Can explain how backpropagation and gradient descent train a network.
  • Can describe convolutional, recurrent and transformer architectures and what each suits.
Develops it

Material that explains the structure of neural networks and deep learning, usually with diagrams and code that builds a small network.

Only mentions it

A pre-trained network used as a black box, or a text that calls a model 'a deep neural network' in passing.

Alignment terms
neural networkneural networksperceptronmultilayer perceptronhidden layergradient descentconvolutional neural networkrecurrent neural networklstm

Read in a resource's text beside the domain group. They are never compiled into a search.

Neighbours

Descriptor be6a4b4e832f

How a vocabulary becomes a search

Every candidate must match both concept groups in its title, description or keywords before any content is downloaded. Precision warnings are recorded for audit; they never silently cancel positive evidence.

  1. Official name and description
  2. AI/ML terms and domain terms
  3. Zenodo, arXiv and GitHub syntax
  4. Metadata relevance gate
Mandatory AI/ML group
artificial intelligencemachine learninggenerative AIdeep learningreinforcement learninglarge language modelAI

GitHub's repository search takes one phrase at a time. Measured against the live endpoint, a parenthesised OR group returns nothing at all where each term alone returns thousands, and the 256-character limit rejects a long group outright — so that lane issues one query per term and stops as soon as the competency is satisfied.

coverage-vocabulary-1.3.0+sha256:08ad2cd19868 · catalogue sha256:04970bfc77255b1f

What a descriptor is

A descriptor is how the alignment reads a competency: what a learner who has it can do, what a resource has to do to develop it, what only mentions it, the phrases its subject is written in, its false friends, and how to tell it from the competencies that share its words. The definition above it stays the authority.

Every descriptor is a draft until a partner approves it; 0 of 104 are approved. Read the alignment rubric →

competency-descriptors-1.0.0+sha256:3cc741a61ced