US Patent Application 18212289. INQUIRY-BASED DEEP LEARNING simplified abstract
Contents
INQUIRY-BASED DEEP LEARNING
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Fethiye Asli Celikyilmaz of Kirkland WA (US)
Chong Wang of Bellevue WA (US)
INQUIRY-BASED DEEP LEARNING - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 18212289 Titled 'INQUIRY-BASED DEEP LEARNING'
Simplified Explanation
This abstract describes a system and method for inquiry-based deep learning. It involves selecting a content segment from a body of content and comparing it to another segment to identify a unique element. This unique element is then stored in memory. A question is generated based on the content segment, and the memory is used to compute an answer. An action is then initiated based on the answer. This process allows for the encoding of content segments into memory and focuses deep learning operations on specific segments through incremental questioning.
Original Abstract Submitted
Systems and methods are disclosed for inquiry-based deep learning. In one implementation, a first content segment is selected from a body of content. The content segment includes a first content element. The first content segment is compared to a second content segment to identify a content element present in the first content segment that is not present in the second content segment. Based on an identification of the content element present in the first content segment that is not present in the second content segment, the content element is stored in a session memory. A first question is generated based on the first content segment. The session memory is processed to compute an answer to the first question. An action is initiated based on the answer. Using deep learning, content segments can be encoded into memory. Incremental questioning can serve to focus various deep learning operations on certain content segments.
