TECHNIQUES FOR ADAPTIVE MULTI-LEVEL RECOMMENDATION USING HIERARCHICAL MIXTURE-OF-EXPERTS FRAMEWORK
卷宗概要
发明人
Maryam ESMAEILI; Justin Derrick BASILICO; Christoph KOFLER; Inbar NAOR; Jiangwei PAN; Jin WANG
IPC 分类
CPC 分类
Techniques for training a hierarchical model include concurrently training a first model and a second model of the hierarchical model using first training data to update first parameters of the first model and second parameters of the second model, wherein output from the first model is provided to the second model. Upon determining that a performance metric has met one or more criteria, the first parameters are frozen to generate frozen first parameters. The second model is then further trained using second training data, wherein the second training data is presented to the first model with the frozen first parameters and the second model.
原文(中文)
Techniques for training a hierarchical model include concurrently training a first model and a second model of the hierarchical model using first training data to update first parameters of the first model and second parameters of the second model, wherein output from the first model is provided to the second model. Upon determining that a performance metric has met one or more criteria, the first parameters are frozen to generate frozen first parameters. The second model is then further trained using second training data, wherein the second training data is presented to the first model with the frozen first parameters and the second model.
登录后阅读全文
已显示权利要求 1。免费注册即可阅读全部 20 项权利要求、说明书全文、全部附图、翻译和法律状态。
- 全部权利要求
- 附图说明