Nanopublication: RAKmi8CK-U

Full identifier: https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0

Raw formats: TriG(html,txt), JSON-LD(txt), N-Quads(txt), XML(txt)

Checking for updates...

 CoSMO Semantic Post SemanticPost comment approve/disapprove edit as derived nanopublication

This is the identifier for the assertion of this nanopublication. https://w3id.org/np/RAKmi8CK-U...#assertion this assertion http://www.w3.org/2000/01/rdf-schema#comment comment (this is a literal) " Evolver, model merging in a genetic algorithm Improves on current merging techniques (my beloved TIES 🫣 ) Train diverse models Merge regularly or take diff between two models Update some parameters Keep if good Repeat https://arxiv.org/abs/2406.12208 @jingli9111 @banting_liu @576gsk https://twitter.com/LChoshen/status/1803410440535326786/photo/1 Merging is aimed at taking many models and getting one that generalizes better, there are various methods for it, read more e.g. on TIES https://x.com/prateeky2806/status/1665759148380758022 Genetic algorithms evolve models, in steps: Create mutations (here new m = m_old + a(m_1-m_2)) m are models a some constant Crossover, take some of the mutation and apply it, for each parameter randomly keep m_old or update to m_new Survive, keep only the best performing on val By sometimes merging and sometimes evolving (and dev sets) they improve over all current methods https://twitter.com/LChoshen/status/1803410445635653960/photo/1 In some sense, this can be seen as a better search in the region between the merged models, which we know is not equally good but all better than the edges https://x.com/LChoshen/status/1729488495515713672 https://twitter.com/LChoshen/status/1803410447246250483/photo/1 " .
This is the identifier for the assertion of this nanopublication. https://w3id.org/np/RAKmi8CK-U...#assertion this assertion https://schema.org/keywords keywords (this is a literal) "TIES" .
This is the identifier for the assertion of this nanopublication. https://w3id.org/np/RAKmi8CK-U...#assertion this assertion https://schema.org/keywords keywords (this is a literal) "evolver" .
This is the identifier for the assertion of this nanopublication. https://w3id.org/np/RAKmi8CK-U...#assertion this assertion https://schema.org/keywords keywords (this is a literal) "genetic\_algorithms" .
This is the identifier for the assertion of this nanopublication. https://w3id.org/np/RAKmi8CK-U...#assertion this assertion https://schema.org/keywords keywords (this is a literal) "knowledge\_fusion" .
This is the identifier for the assertion of this nanopublication. https://w3id.org/np/RAKmi8CK-U...#assertion this assertion https://schema.org/keywords keywords (this is a literal) "model\_merging" .
This is the identifier for the assertion of this nanopublication. https://w3id.org/np/RAKmi8CK-U...#assertion The assertion above http://www.w3.org/ns/prov#wasGeneratedBy wasGeneratedBy This is a local identifier minted within the nanopublication. https://w3id.org/np/RAKmi8CK-U...#activity activity .
This is the identifier for this whole nanopublication. https://w3id.org/np/RAKmi8CK-U... This nanopublication date and time when the nanopublication was created http://purl.org/dc/terms/created was created on (this is a literal) "2024-09-12T18:58:02.418Z" .
This is a local identifier minted within the nanopublication. https://w3id.org/np/RAKmi8CK-U...#sig sig http://purl.org/nanopub/x/hasSignatureTarget has as target This is the identifier for this whole nanopublication. https://w3id.org/np/RAKmi8CK-U... this nanopublication .
This is a local identifier minted within the nanopublication. https://w3id.org/np/RAKmi8CK-U...#sig sig http://purl.org/nanopub/x/hasAlgorithm has the algorithm (this is a literal) "RSA" .

Sensenets, 12 Sep 2024, 18:58:02 UTC

show references