17934527. DEEP LEARNING MODEL FOR HIGH RESOLUTION PREDICTIONS simplified abstract (QUALCOMM Incorporated)
Contents
- 1 DEEP LEARNING MODEL FOR HIGH RESOLUTION PREDICTIONS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DEEP LEARNING MODEL FOR HIGH RESOLUTION PREDICTIONS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
DEEP LEARNING MODEL FOR HIGH RESOLUTION PREDICTIONS
Organization Name
Inventor(s)
Chieh-Ming Kuo of Taoyuan (TW)
Michel Adib Sarkis of San Diego CA (US)
DEEP LEARNING MODEL FOR HIGH RESOLUTION PREDICTIONS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17934527 titled 'DEEP LEARNING MODEL FOR HIGH RESOLUTION PREDICTIONS
Simplified Explanation
The abstract describes a patent application related to optimizing deep learning models by adjusting prediction outputs based on quantization ranges.
- Systems and techniques for deep learning model optimizations:
- Generating multiple prediction outputs for different output channels based on neural network processing.
- Identifying prediction outputs outside quantization range and adjusting them accordingly.
- Clamping prediction outputs to quantization range.
- Generating a single channel output based on adjusted prediction outputs.
Potential Applications
This technology could be applied in various fields such as image recognition, natural language processing, and autonomous driving systems.
Problems Solved
This innovation helps improve the accuracy and efficiency of deep learning models by optimizing prediction outputs within quantization ranges.
Benefits
- Enhanced performance of deep learning models. - Improved accuracy of predictions. - Increased efficiency in processing data.
Potential Commercial Applications
This technology could be utilized in industries such as healthcare for medical image analysis, retail for customer behavior prediction, and finance for fraud detection.
Possible Prior Art
One possible prior art could be the use of quantization techniques in machine learning models to optimize prediction outputs.
What are the specific neural network models used in this patent application?
The abstract does not specify the exact neural network models used in this patent application.
How does this technology compare to existing quantization methods in deep learning models?
The article does not provide a direct comparison between this technology and existing quantization methods in deep learning models.
Original Abstract Submitted
Systems and techniques are provided for deep learning model optimizations. An example process can include generating, based on processing data using a neural network model, a plurality of prediction outputs associated with a plurality of output channels corresponding to a multi-channel prediction target; determining that a prediction output from the plurality of prediction outputs has a value that is outside of a quantization range and one or more remaining prediction outputs from the plurality of prediction outputs have a respective value that is within the quantization range; clamping the prediction output based on the quantization range; and generating a single channel output based on the clamped prediction output and the one or more remaining prediction outputs.
