17863963. APPARATUS AND METHOD WITH NEURAL NETWORK OPERATION simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
Contents
APPARATUS AND METHOD WITH NEURAL NETWORK OPERATION
Organization Name
Inventor(s)
APPARATUS AND METHOD WITH NEURAL NETWORK OPERATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 17863963 titled 'APPARATUS AND METHOD WITH NEURAL NETWORK OPERATION
Simplified Explanation
The abstract describes a neural network operation apparatus and method. Here is a simplified explanation of the abstract:
- The neural network operation apparatus includes an internal storage to store data for performing a neural network operation.
- It has an arithmetic logical unit (ALU) to perform an operation between the stored data and main data based on an operation control signal.
- An adder is used to add the output of the ALU and the output of a first multiplexer.
- The first multiplexer selects either the output of the adder or the output of the ALU based on a reset signal.
- A second multiplexer selects either the main data or a quantization result of the stored data based on a phase signal.
- A controller is responsible for controlling the ALU, the first multiplexer, and the second multiplexer based on the operation control signal, the reset signal, and the phase signal.
Potential applications of this technology:
- Neural network operations in artificial intelligence systems
- Machine learning algorithms
- Deep learning models
Problems solved by this technology:
- Efficient and optimized neural network operations
- Reduction of computational complexity
- Improved performance and accuracy in neural network processing
Benefits of this technology:
- Faster and more efficient neural network operations
- Reduced power consumption
- Improved accuracy and reliability in neural network processing
Original Abstract Submitted
A neural network operation apparatus and method are provided. The neural network operation apparatus includes an internal storage configured to store data to perform a neural network operation, an arithmetic logical unit (ALU) configured to perform an operation between the stored data and main data based on an operation control signal, an adder configured to add an output of the ALU and an output of a first multiplexer, wherein the first multiplexer is configured to output one of an output of the adder and the output of the ALU based on a reset signal, a second multiplexer configured to output one of the main data and a quantization result of the stored data based on a phase signal, and a controller configured to control the ALU, the first multiplexer, and the second multiplexer based on the operation control signal, the reset signal, and the phase signal.
