Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386328598> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4386328598 endingPage "19" @default.
- W4386328598 startingPage "402" @default.
- W4386328598 abstract "A significant challenge in self-driving technology involves the domain-specific training of prediction models on intentions of other surrounding vehicles. Separately processing domain-specific models requires substantial human resources, time, and equipment for data collection and training. For instance, substantial difficulties arise when directly applying a prediction model developed with data from China to the United States market due to complex factors such as differing driving behaviors and traffic rules. The emergence of transfer learning seems to offer solutions, enabling the reuse of models and data to enhance prediction efficiency across international markets. However, many transfer learning methods require a comparison between source and target data domains to determine what can be transferred, a process that can often be legally restricted. A specialized area of transfer learning, known as network-based transfer, could potentially provide a solution. This approach involves pre-training and fine-tuning student models using selected parameters from a teacher model. However, as networks typically have a large number of parameters, it raises questions about the most efficient methods for parameter selection to optimize transfer learning. An automatic parameter selector through reinforcement learning has been developed in this paper, named Automatic Transfer Selector via Reinforcement Learning. This technique enhances the efficiency of parameter selection for transfer prediction between international self-driving markets, in contrast to manual methods. With this innovative approach, technicians are relieved from the labor-intensive task of testing each parameter combination, or enduring lengthy training periods to evaluate the impact of prediction transfer. Experiments have been conducted using a temporal convolutional neural network fully trained with the data from the Chinese market and one month's US data, focusing on improving the training efficiency of specific driving scenarios in the US. Results show that the proposed approach significantly improves the prediction transfer process." @default.
- W4386328598 created "2023-09-01" @default.
- W4386328598 creator A5024763644 @default.
- W4386328598 creator A5065592637 @default.
- W4386328598 creator A5068707543 @default.
- W4386328598 creator A5087505541 @default.
- W4386328598 date "2023-08-31" @default.
- W4386328598 modified "2023-09-27" @default.
- W4386328598 title "Reinforcement learning methods for network-based transfer parameter selection" @default.
- W4386328598 doi "https://doi.org/10.20517/ir.2023.23" @default.
- W4386328598 hasPublicationYear "2023" @default.
- W4386328598 type Work @default.
- W4386328598 citedByCount "0" @default.
- W4386328598 crossrefType "journal-article" @default.
- W4386328598 hasAuthorship W4386328598A5024763644 @default.
- W4386328598 hasAuthorship W4386328598A5065592637 @default.
- W4386328598 hasAuthorship W4386328598A5068707543 @default.
- W4386328598 hasAuthorship W4386328598A5087505541 @default.
- W4386328598 hasBestOaLocation W43863285981 @default.
- W4386328598 hasConcept C111919701 @default.
- W4386328598 hasConcept C119857082 @default.
- W4386328598 hasConcept C127413603 @default.
- W4386328598 hasConcept C134306372 @default.
- W4386328598 hasConcept C150899416 @default.
- W4386328598 hasConcept C154945302 @default.
- W4386328598 hasConcept C201995342 @default.
- W4386328598 hasConcept C2780451532 @default.
- W4386328598 hasConcept C33923547 @default.
- W4386328598 hasConcept C36503486 @default.
- W4386328598 hasConcept C41008148 @default.
- W4386328598 hasConcept C81917197 @default.
- W4386328598 hasConcept C97541855 @default.
- W4386328598 hasConcept C98045186 @default.
- W4386328598 hasConceptScore W4386328598C111919701 @default.
- W4386328598 hasConceptScore W4386328598C119857082 @default.
- W4386328598 hasConceptScore W4386328598C127413603 @default.
- W4386328598 hasConceptScore W4386328598C134306372 @default.
- W4386328598 hasConceptScore W4386328598C150899416 @default.
- W4386328598 hasConceptScore W4386328598C154945302 @default.
- W4386328598 hasConceptScore W4386328598C201995342 @default.
- W4386328598 hasConceptScore W4386328598C2780451532 @default.
- W4386328598 hasConceptScore W4386328598C33923547 @default.
- W4386328598 hasConceptScore W4386328598C36503486 @default.
- W4386328598 hasConceptScore W4386328598C41008148 @default.
- W4386328598 hasConceptScore W4386328598C81917197 @default.
- W4386328598 hasConceptScore W4386328598C97541855 @default.
- W4386328598 hasConceptScore W4386328598C98045186 @default.
- W4386328598 hasIssue "3" @default.
- W4386328598 hasLocation W43863285981 @default.
- W4386328598 hasOpenAccess W4386328598 @default.
- W4386328598 hasPrimaryLocation W43863285981 @default.
- W4386328598 hasRelatedWork W2946016983 @default.
- W4386328598 hasRelatedWork W2960456850 @default.
- W4386328598 hasRelatedWork W3021430260 @default.
- W4386328598 hasRelatedWork W4281645081 @default.
- W4386328598 hasRelatedWork W4308262314 @default.
- W4386328598 hasRelatedWork W4312200629 @default.
- W4386328598 hasRelatedWork W4319083788 @default.
- W4386328598 hasRelatedWork W4379662533 @default.
- W4386328598 hasRelatedWork W4382286161 @default.
- W4386328598 hasRelatedWork W4386213806 @default.
- W4386328598 hasVolume "3" @default.
- W4386328598 isParatext "false" @default.
- W4386328598 isRetracted "false" @default.
- W4386328598 workType "article" @default.