18069974. REGULARIZING NEURAL NETWORKS WITH DATA QUANTIZATION USING EXPONENTIAL FAMILY PRIORS simplified abstract (QUALCOMM Incorporated)
Contents
- 1 REGULARIZING NEURAL NETWORKS WITH DATA QUANTIZATION USING EXPONENTIAL FAMILY PRIORS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 REGULARIZING NEURAL NETWORKS WITH DATA QUANTIZATION USING EXPONENTIAL FAMILY PRIORS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Key Features and Innovation
- 1.6 Potential Applications
- 1.7 Problems Solved
- 1.8 Benefits
- 1.9 Commercial Applications
- 1.10 Prior Art
- 1.11 Frequently Updated Research
- 1.12 Questions about Video Data Processing
- 1.13 Original Abstract Submitted
REGULARIZING NEURAL NETWORKS WITH DATA QUANTIZATION USING EXPONENTIAL FAMILY PRIORS
Organization Name
Inventor(s)
Thomas Alexander Ryder of San Diego CA (US)
Muhammed Zeyd Coban of Carlsbad CA (US)
Marta Karczewicz of San Diego CA (US)
REGULARIZING NEURAL NETWORKS WITH DATA QUANTIZATION USING EXPONENTIAL FAMILY PRIORS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18069974 titled 'REGULARIZING NEURAL NETWORKS WITH DATA QUANTIZATION USING EXPONENTIAL FAMILY PRIORS
Simplified Explanation
The patent application describes a process for processing video data using a neural network-based video encoder.
- The process involves quantization steps and applying an exponential-family prior to generate output evaluations.
- It includes generating a total loss value for the video encoder and training it based on this value.
Key Features and Innovation
- Processing video data using a neural network-based video encoder.
- Incorporating quantization steps and an exponential-family prior for output evaluations.
- Generating a total loss value for the video encoder to aid in training.
Potential Applications
This technology can be used in video compression, video analysis, and video streaming applications.
Problems Solved
- Efficient processing of video data.
- Improved video quality and compression.
- Enhanced training of neural network-based video encoders.
Benefits
- Higher quality video output.
- More efficient video compression.
- Enhanced performance of neural network-based video encoders.
Commercial Applications
- This technology can be utilized in video streaming services, video surveillance systems, and video editing software to improve video processing and compression efficiency.
Prior Art
Readers can explore prior art related to neural network-based video encoders, video compression techniques, and video processing algorithms.
Frequently Updated Research
Stay updated on the latest advancements in neural network-based video encoding, video compression, and video processing technologies.
Questions about Video Data Processing
How does the neural network-based video encoder improve video processing efficiency?
The neural network-based video encoder enhances video processing efficiency by utilizing quantization steps and an exponential-family prior for output evaluations, leading to improved video quality and compression.
What are the potential applications of this technology beyond video processing?
This technology can also be applied in fields such as image processing, computer vision, and artificial intelligence for various data processing tasks.
Original Abstract Submitted
Systems and techniques are described for processing video data. For instance, a process can include processing a frame of video data using a first layer of a neural network-based video encoder, the neural network-based video encoder performing at least one quantization step. The process can further include applying an exponential-family prior to an output of the first layer of the neural network-based video encoder to generate a first layer output evaluation, generating a total loss value for the neural network-based video encoder based on a sum of a loss value for the neural network-based video encoder and the first layer output evaluation, and training the neural network-based video encoder based on the total loss value.
