Samsung electronics co., ltd. (20240112708). DEVICE AND METHOD WITH COMPUTATIONAL MEMORY simplified abstract
Contents
- 1 DEVICE AND METHOD WITH COMPUTATIONAL MEMORY
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DEVICE AND METHOD WITH COMPUTATIONAL MEMORY - 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 Unanswered Questions
- 1.11 Original Abstract Submitted
DEVICE AND METHOD WITH COMPUTATIONAL MEMORY
Organization Name
Inventor(s)
Soon-Wan Kwon of Suwon-si (KR)
Seungchul Jung of Suwon-si (KR)
DEVICE AND METHOD WITH COMPUTATIONAL MEMORY - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240112708 titled 'DEVICE AND METHOD WITH COMPUTATIONAL MEMORY
Simplified Explanation
The abstract describes a computational memory device that includes memory banks for storing weight data of a neural network model, a weight memory block for providing weight data in response to a weight request, a computational memory block for performing multiply-accumulate operations between weight data and input data, and a communication interface for communication between the weight memory block and the computational memory block.
- Memory banks store weight data of a neural network model.
- Weight memory block provides weight data in response to a weight request.
- Computational memory block performs multiply-accumulate operations between weight data and input data.
- Communication interface facilitates communication between the weight memory block and the computational memory block.
Potential Applications
This technology could be applied in:
- Artificial intelligence
- Machine learning
- Robotics
Problems Solved
This technology helps in:
- Improving computational efficiency
- Reducing memory access latency
- Enhancing neural network performance
Benefits
The benefits of this technology include:
- Faster processing speeds
- Lower power consumption
- Improved accuracy in neural network computations
Potential Commercial Applications
The potential commercial applications of this technology could be seen in:
- Data centers
- Edge computing devices
- Autonomous vehicles
Possible Prior Art
One possible prior art for this technology could be:
- Research on computational memory devices in the field of neuromorphic computing.
Unanswered Questions
How does this technology compare to traditional neural network models?
This article does not provide a direct comparison between this technology and traditional neural network models in terms of performance, efficiency, and accuracy.
What are the limitations of this computational memory device?
The article does not discuss any potential limitations or constraints of the computational memory device, such as scalability, compatibility with different neural network architectures, or cost implications.
Original Abstract Submitted
a computational memory device and a method using the computational memory device are provided. the computational memory device includes memory banks configured to store weight data of a neural network model and a weight memory block configured to provide at least some of the weight data from memory banks in response to a weight request, a computational memory block physically stacked on the weight memory block such faces of the respective blocks face each other, the computational memory block configured to perform a multiply-accumulate (mac) operation between the at least some of the weight data and at least some of input data by using a bit cell array including bit cells, and a communication interface configured to perform communication between the weight memory block and the computational memory block.