18074916. Semiconductor Package simplified abstract (Samsung Electronics Co., Ltd.)
Contents
Semiconductor Package
Organization Name
Inventor(s)
Chol-Min Kim of Changwon-si (KR)
Tae-Kyeong Ko of Hwaseong-si (KR)
Semiconductor Package - A simplified explanation of the abstract
This abstract first appeared for US patent application 18074916 titled 'Semiconductor Package
Simplified Explanation
An electronic device with a graphic processor and memory device is described in this patent application. The device includes an artificial neural network engine that helps an object recognition model learn using learning data and weights, resulting in a learned object recognition model. The memory device divides a feature vector into two sub feature vectors and performs calculations using these sub feature vectors and the weights to provide object recognition results. The artificial neural network engine performs parallel calculations using the sub feature vectors and weights to provide additional object recognition results.
- An electronic device with a graphic processor and memory device is described.
- The device includes an artificial neural network engine for object recognition.
- The neural network engine helps the object recognition model learn using learning data and weights.
- The memory device divides a feature vector into two sub feature vectors.
- The memory device performs calculations using the sub feature vectors and weights to provide object recognition results.
- The artificial neural network engine performs parallel calculations using the sub feature vectors and weights to provide additional object recognition results.
Potential Applications
This technology has potential applications in various fields, including:
- Computer vision systems
- Autonomous vehicles
- Robotics
- Surveillance systems
- Image and video analysis
Problems Solved
This technology addresses the following problems:
- Improving object recognition accuracy
- Enhancing the efficiency of object recognition models
- Enabling parallel calculations for faster results
- Optimizing memory usage in electronic devices
Benefits
The benefits of this technology include:
- Improved object recognition performance
- Faster and more efficient object recognition
- Enhanced capabilities for computer vision systems
- Increased accuracy in autonomous vehicles and robotics
- Improved surveillance and security systems
Original Abstract Submitted
An electronic device includes a graphic processor and a memory device. The graphic processor includes an artificial neural network engine that makes an object recognition model learn by using learning data and weights to provide a learned object recognition model. The memory device, divides a feature vector into a first sub feature vector and a second feature vector, and performs a first calculation to apply the second sub feature vector and the weights to the learned object recognition model to provide a second object recognition result. The artificial neural network engine performs a second calculation to apply the first sub feature vector and the weights to the learned object recognition model to provide a first object recognition result and provides the first object recognition result to the memory device. The second calculation is performed in parallel with the first calculation.
