View source for Qualcomm incorporated (20240205427). INSTANCE-ADAPTIVE IMAGE AND VIDEO COMPRESSION USING MACHINE LEARNING SYSTEMS simplified abstract

=INSTANCE-ADAPTIVE IMAGE AND VIDEO COMPRESSION USING MACHINE LEARNING SYSTEMS=


==Organization Name==

[[:Category:qualcomm incorporated|qualcomm incorporated]]


[[Category:qualcomm incorporated]]

==Inventor(s)==

[[:Category:Ties Jehan Van Rozendaal of Amsterdam (NL)|Ties Jehan Van Rozendaal of Amsterdam (NL)]][[Category:Ties Jehan Van Rozendaal of Amsterdam (NL)]]

[[:Category:Iris Anne Marie Huijben of Eindhoven (NL)|Iris Anne Marie Huijben of Eindhoven (NL)]][[Category:Iris Anne Marie Huijben of Eindhoven (NL)]]

[[:Category:Taco Sebastiaan Cohen of Amsterdam (NL)|Taco Sebastiaan Cohen of Amsterdam (NL)]][[Category:Taco Sebastiaan Cohen of Amsterdam (NL)]]

==INSTANCE-ADAPTIVE IMAGE AND VIDEO COMPRESSION USING MACHINE LEARNING SYSTEMS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240205427 titled 'INSTANCE-ADAPTIVE IMAGE AND VIDEO COMPRESSION USING MACHINE LEARNING SYSTEMS

The abstract describes techniques for compressing data using machine learning systems and tuning these systems for compression. An example process involves a neural network compression system receiving input data, determining updates for the system, generating compressed versions of the input data and model parameters, and outputting these compressed versions for transmission.

* Neural network compression system compresses data using machine learning
* Updates model parameters for compression based on input data
* Generates compressed versions of input data and model parameters
* Outputs compressed data for transmission

Potential Applications:
- Data compression in various industries such as telecommunications, image processing, and data storage
- Enhancing data transmission efficiency and reducing storage requirements

Problems Solved:
- Efficient data compression using machine learning systems
- Optimizing model parameters for better compression results

Benefits:
- Improved data compression efficiency
- Reduced storage and transmission costs
- Enhanced data processing speed

Commercial Applications:
- Telecommunications companies for efficient data transmission
- Image processing companies for reducing storage requirements
- Data storage companies for optimizing storage space

Questions about Data Compression using Machine Learning:
1. How does the neural network compression system determine updates for compression?
2. What are the potential challenges in implementing machine learning-based data compression techniques?

Frequently Updated Research:
- Stay updated on advancements in machine learning algorithms for data compression
- Monitor research on optimizing model parameters for better compression results.


==Original Abstract Submitted==

techniques are described for compressing data using machine learning systems and tuning machine learning systems for compressing the data. an example process can include receiving, by a neural network compression system (e.g., trained on a training dataset), input data for compression by the neural network compression system. the process can include determining a set of updates for the neural network compression system, the set of updates including updated model parameters tuned using the input data. the process can include generating, by the neural network compression system using a latent prior, a first bitstream including a compressed version of the input data. the process can further include generating, by the neural network compression system using the latent prior and a model prior, a second bitstream including a compressed version of the updated model parameters. the process can include outputting the first bitstream and the second bitstream for transmission to a receiver.



[[Category:H04N19/184]]
[[Category:G06N3/045]]
[[Category:G06N3/088]]
[[Category:CPC_H04N19/184]]