An ontology modeling classes and relationships describing deep learning networks, their component layers and activation functions, machine learning methods, as well as AI/ML potential biases.
There may be implicit linkages between branches - these should be made explicit
e.g model performs task
This should be aligned with definitions - ideally definitions should refer to terms in this ontology or other ontologies
this could also be a useful way to group things other than is-a. E.g. LLMs and Markov Models may live in different subhierarchies but they would be united by next token prediction
There may be implicit linkages between branches - these should be made explicit
e.g model performs task
This should be aligned with definitions - ideally definitions should refer to terms in this ontology or other ontologies
this could also be a useful way to group things other than is-a. E.g. LLMs and Markov Models may live in different subhierarchies but they would be united by next token prediction