发明名称 SYSTEMS AND METHODS FOR LEARNING NEW TRAINED CONCEPTS USED TO RETRIEVE CONTENT RELEVANT TO THE CONCEPTS LEARNED
摘要 A system configured for learning new trained concepts used to retrieve content relevant to the concepts learned. The system may comprise one or more hardware processors configured by machine-readable instructions to obtain one or more digital media items. The one or more hardware processors may be further configured to obtain an indication conveying a concept to be learned from the one or more digital media items. The one or more hardware processors may be further configured to receive feedback associated with individual ones of the one or more digital media items. The one or more hardware processors may be configured to obtain individual neural network representations for the individual ones of the one or more digital media items. The one or more hardware processors may be configured to determine a trained concept based on the feedback and the neural network representations of the one or more digital media items.
申请公布号 US2017039468(A1) 申请公布日期 2017.02.09
申请号 US201514820454 申请日期 2015.08.06
申请人 CLARIFAI, INC. 发明人 Zeiler Matthew D.
分类号 G06N3/08;G06F17/30 主分类号 G06N3/08
代理机构 代理人
主权项 1. A system configured for learning new trained concepts used to retrieve content relevant to the concepts learned, the system comprising: one or more hardware processors configured by machine-readable instructions to: obtain one or more digital media items;obtain an indication conveying a concept to be learned from the one or more digital media items;receive feedback associated with individual ones of the one or more digital media items, wherein the feedback is based on one or both of (1) selection of one or more positive examples of the concept to be learned from the one or more digital media items, or (2) selection of one or more negative examples of the concept to be learned from the one or more digital media items, a given positive example being a digital media item comprising the concept to be learned, and a given negative example being a digital media item lacking the concept to be learned;obtain individual neural network representations for the individual ones of the one or more digital media items, a given neural network representation including one or more neural network layers; anddetermine a trained concept based on (1) the feedback and (2) the neural network representations of the one or more digital media items, the trained concept being usable for retrieving digital media items relevant to the concept to be learned.
地址 New York NY US
您可能感兴趣的专利