17957508. Selecting a Tiling Scheme for Processing Instances of Input Data Through a Neural Netwok simplified abstract (ATI TECHNOLOGIES ULC)
Contents
- 1 Selecting a Tiling Scheme for Processing Instances of Input Data Through a Neural Netwok
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 Selecting a Tiling Scheme for Processing Instances of Input Data Through a Neural Netwok - 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
Selecting a Tiling Scheme for Processing Instances of Input Data Through a Neural Netwok
Organization Name
Inventor(s)
Akila Subramaniam of Allen TX (US)
Tung Chuen Kwong of Richmond Hill (CA)
Juanjo Noguera of Santa Clara CA (US)
Selecting a Tiling Scheme for Processing Instances of Input Data Through a Neural Netwok - A simplified explanation of the abstract
This abstract first appeared for US patent application 17957508 titled 'Selecting a Tiling Scheme for Processing Instances of Input Data Through a Neural Netwok
Simplified Explanation
The abstract describes an electronic device that uses different tiling schemes to process input data through a neural network. The device selects a tiling scheme based on information about the neural network and properties of the processing circuitry, then divides the input data into portions according to the selected scheme for processing in the neural network.
- The electronic device uses a variety of tiling schemes to process input data through a neural network.
- Each tiling scheme divides input data into different portions for processing in the neural network.
- The device selects a tiling scheme based on information about the neural network and properties of the processing circuitry.
- Input data is divided into portions according to the selected tiling scheme, processed separately in the neural network, and then combined to generate an output.
Potential Applications
This technology could be applied in various fields such as image recognition, natural language processing, and pattern recognition tasks where neural networks are used for processing complex data.
Problems Solved
This technology helps optimize the processing of input data in neural networks by selecting the most suitable tiling scheme based on the neural network's characteristics and the device's properties. It improves efficiency and accuracy in processing tasks.
Benefits
- Improved efficiency in processing input data through neural networks - Enhanced accuracy in generating outputs from neural network processing - Adaptability to different neural network structures and processing requirements
Potential Commercial Applications
Optimized neural network processing devices for industries such as healthcare (medical image analysis), finance (fraud detection), and autonomous vehicles (object recognition).
Possible Prior Art
One possible prior art could be the use of tiling schemes in image processing algorithms to divide images into smaller parts for analysis in computer vision applications.
Unanswered Questions
How does the device determine the most suitable tiling scheme for a specific neural network and input data?
The abstract mentions that the device selects a tiling scheme based on information about the neural network and properties of the processing circuitry, but it does not specify the exact criteria or algorithms used for this selection process.
Are there any limitations or drawbacks to using different tiling schemes for processing input data in neural networks?
While the abstract highlights the benefits of using different tiling schemes, it does not address any potential limitations or challenges that may arise from this approach, such as increased computational complexity or trade-offs in processing speed.
Original Abstract Submitted
An electronic device uses a tiling scheme selected from among a set of tiling schemes for processing instances of input data through a neural network. Each of the tiling schemes is associated with a different arrangement of portions into which instances of input data are divided for processing in the neural network. In operation, processing circuitry in the electronic device acquires information about a neural network and properties of the processing circuitry. The processing circuitry then selects a given tiling scheme from among a set of tiling schemes based on the information. The processing circuitry next processes instances of input data in the neural network using the given tiling scheme. Processing each instance of input data in the neural network includes dividing the instance of input data into portions based on the given tiling scheme, separately processing each of the portions in the neural network, and combining the respective outputs to generate an output for the instance of input data.
