Back to results
US 2026/0017501 A1Published application
Model-code separation architecture for data compression using sum-product networks
AssigneeMassachusetts Institute of Technology
InventorsTejas Kumar Jayashankar, Gregory W. Wornell
Life of this patent
Estimating the term…
Abstract
According to some embodiments, a method of decoding data includes: receiving data compressed by a universal encoder and a data model based on a sum-product network (SPN) representing statistical structure inherent to source data, the source data corresponding to an uncompressed version of the data; and decompressing the data using the data model.
Claims18
A method of decoding data, the method comprising:
- receiving data compressed by a universal encoder and a data model based on a sum-product network (SPN) representing statistical structure inherent to source data, the source data corresponding to an uncompressed version of the data;
- and
- decompressing the data using the data model.
A decoder for use in a data compression system with model-code separation, the decoder comprising:
- one or more processors configured to:
- receive data compressed by a universal encoder and a data model based on a sum-product network (SPN) representing statistical structure inherent to source data, the source data corresponding to an uncompressed version of the data;
- and
- decompress the data using the data model.
1 more element
Dependencies are inferred from the claim text.