首页|Study Results from Tianjin University Update Understanding of Machine Learning [Concurrent Classifier Error Detection (Cced) In Large Scale Machine Learning Sys tems]
Study Results from Tianjin University Update Understanding of Machine Learning [Concurrent Classifier Error Detection (Cced) In Large Scale Machine Learning Sys tems]
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learn ing have been published. According to news reporting from Tianjin, People's Repu blic of China, by NewsRx journalists, research stated, "The complexity of machin e learning (ML) systems increases each year. As these systems are widely utilize d, ensuring their reliable operation is becoming a design requirement." Financial support for this research came from FUN4DATE. The news correspondents obtained a quote from the research from Tianjin Universi ty, "Traditional error detection mechanisms introduce circuit or time redundancy that significantly impacts system performance. An alternative is the use of con current error detection (CED) schemes that operate in parallel with the system a nd exploit their properties to detect errors. CED is attractive for large ML sys tems because it can potentially reduce the cost of error detection. In this arti cle, we introduce concurrent classifier error detection (CCED), a scheme to impl ement CED in ML systems using a concurrent ML classifier to detect errors. CCED identifies a set of check signals in the main ML system and feed them to the con current ML classifier that is trained to detect errors. The proposed CCED scheme has been implemented and evaluated on two widely used large-scale ML models: Co ntrastive language-image pretraining (CLIP) used for image classification and bi directional encoder representations from transformers (BERT) used for natural la nguage applications."
TianjinPeople's Republic of ChinaAsi aCyborgsEmerging TechnologiesMachine LearningTianjin University
NETL
NSTL
