17425216. ELECTRONIC APPARATUS AND CONTROL METHOD THEREOF simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
Contents
ELECTRONIC APPARATUS AND CONTROL METHOD THEREOF
Organization Name
Inventor(s)
ELECTRONIC APPARATUS AND CONTROL METHOD THEREOF - A simplified explanation of the abstract
This abstract first appeared for US patent application 17425216 titled 'ELECTRONIC APPARATUS AND CONTROL METHOD THEREOF
Simplified Explanation
The abstract describes an electronic apparatus that performs neural network computations using an artificial intelligence model. The apparatus includes an input interface, a memory to store weights corresponding to the model, and a processor to perform computations based on the weights and input data.
- The electronic apparatus performs neural network computations using an artificial intelligence model.
- It has an input interface to receive input data.
- The memory stores weights that correspond to the artificial intelligence model.
- The processor performs computations based on the weights and input data.
- If the computation result falls within a threshold range, the processor can change the original value within that range to a preset value and perform the computation again using the preset value.
Potential applications of this technology:
- Artificial intelligence systems and applications
- Machine learning algorithms
- Neural network computations in various fields such as image recognition, natural language processing, and data analysis
Problems solved by this technology:
- The ability to change specific values within a threshold range allows for fine-tuning and optimization of neural network computations.
- It provides a mechanism to adjust the weights of the artificial intelligence model based on specific input data, improving the accuracy and performance of the computations.
Benefits of this technology:
- Improved accuracy and performance of neural network computations.
- Flexibility to adjust and optimize the weights of the artificial intelligence model.
- Enhanced capabilities for various applications relying on artificial intelligence and machine learning.
Original Abstract Submitted
An electronic apparatus is provided. The electronic apparatus includes: an input interface; a memory configured to store a plurality of weights corresponding to an artificial intelligence model; and a processor configured to perform a neural network computation with respect to input data provided through the input interface based on the plurality of weights. The processor is also configured to, based on any one or any combination of the input data, the plurality of weights, and a computation result obtained in a process of performing the neural network computation being within a threshold range, change an original value within the threshold range to a preset value and perform the neural network computation based on the preset value.
