18510865. INITIALIZER FOR CIRCLE DISTRIBUTION FOR IMAGE AND VIDEO COMPRESSION AND POSTURE DETECTION simplified abstract (Intel Corporation)
Contents
- 1 INITIALIZER FOR CIRCLE DISTRIBUTION FOR IMAGE AND VIDEO COMPRESSION AND POSTURE DETECTION
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 INITIALIZER FOR CIRCLE DISTRIBUTION FOR IMAGE AND VIDEO COMPRESSION AND POSTURE DETECTION - 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 How does the quadtron perceptron compare to traditional perceptrons in terms of performance and efficiency?
- 1.11 Are there any limitations or drawbacks to using the mixed deterministic and iterative/stochastic approach for circle distribution?
- 1.12 Original Abstract Submitted
INITIALIZER FOR CIRCLE DISTRIBUTION FOR IMAGE AND VIDEO COMPRESSION AND POSTURE DETECTION
Organization Name
Inventor(s)
Pawel Tomkiewicz of Zukowo (PL)
Monica Lucia Martinez-canales of Los Altos CA (US)
INITIALIZER FOR CIRCLE DISTRIBUTION FOR IMAGE AND VIDEO COMPRESSION AND POSTURE DETECTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18510865 titled 'INITIALIZER FOR CIRCLE DISTRIBUTION FOR IMAGE AND VIDEO COMPRESSION AND POSTURE DETECTION
Simplified Explanation
The abstract describes an initializer for circle distribution on a 2D surface using a polar coordinate system, which can also be extended to sphere distribution in a 3D shape. The method combines deterministic and iterative/stochastic approaches, transitioning from polar to cartesian coordinates. It also discusses using the polar system in CPU units for neural network model compression, specifically for a quadtron perceptron.
- The initializer enables circle distribution on a 2D surface using a polar coordinate system.
- It can be extended to sphere distribution in a 3D shape.
- The method combines deterministic and iterative/stochastic approaches.
- Transition from polar to cartesian coordinates for efficient parameter initialization.
- Utilizes the polar system in CPU units for neural network model compression.
- Introduces a quadtron perceptron for solving circle distribution and other problems.
Potential Applications
The technology can be applied in image compression, video compression, motion detection, posture detection, and neural network model compression.
Problems Solved
Efficient initialization of parameters for circle and sphere distribution on 2D and 3D surfaces, respectively. Neural network model compression for improved efficiency and performance.
Benefits
Improved accuracy and efficiency in circle and sphere distribution. Enhanced compression and processing capabilities in various applications.
Potential Commercial Applications
The technology can be utilized in industries such as image processing, video streaming, surveillance systems, and artificial intelligence.
Possible Prior Art
Prior art may include methods for parameter initialization in image processing and neural network compression techniques.
Unanswered Questions
How does the quadtron perceptron compare to traditional perceptrons in terms of performance and efficiency?
The article does not provide a direct comparison between the quadtron perceptron and traditional perceptrons in terms of performance and efficiency.
Are there any limitations or drawbacks to using the mixed deterministic and iterative/stochastic approach for circle distribution?
The article does not address any potential limitations or drawbacks of using the mixed deterministic and iterative/stochastic approach for circle distribution.
Original Abstract Submitted
An initializer for circle distribution on a 2D surface using a polar coordinate system for image compression, video compression, motion detection, and posture detection. The initializer can also be used for sphere distribution in a 3D shape. The initializer uses a mixed deterministic and iterative/stochastic approach. Using the polar coordinate system for initialization enables coverage of the user space, and after parameters are initialized, the method transitions to a cartesian coordinate system. Methods for using the polar system in CPU units by applying an XNOR/AND architecture for neural network model compression are also described. The neural network includes a perceptron for supervised learning of binary classifiers. The unit responsible for multiplication in a MAC architecture can be replaced with a non-linear expressive function. Thus, a neural network having a non-linear expressive perceptron (quadtron) is described for solving circle distribution and other problems.
