17940717. Balance Accuracy and Power Consumption in Integrated Circuit Devices having Analog Inference Capability simplified abstract (Micron Technology, Inc.)
Contents
- 1 Balance Accuracy and Power Consumption in Integrated Circuit Devices having Analog Inference Capability
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 Balance Accuracy and Power Consumption in Integrated Circuit Devices having Analog Inference Capability - 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 Unanswered Questions
- 1.10 Original Abstract Submitted
Balance Accuracy and Power Consumption in Integrated Circuit Devices having Analog Inference Capability
Organization Name
Inventor(s)
Balance Accuracy and Power Consumption in Integrated Circuit Devices having Analog Inference Capability - A simplified explanation of the abstract
This abstract first appeared for US patent application 17940717 titled 'Balance Accuracy and Power Consumption in Integrated Circuit Devices having Analog Inference Capability
Simplified Explanation
The patent application describes a method to balance computation accuracy and energy consumption in artificial neural networks by programming threshold voltages of memory cells and selecting configurations for processing inputs.
- Programming threshold voltages of memory cells to store weight matrices of artificial neural networks
- Selecting configurations for processing inputs using different memory cells
- Performing operations of multiplication and accumulation using memory cells in computations of artificial neural networks
Potential Applications
This technology could be applied in various fields such as:
- Edge computing
- Internet of Things (IoT) devices
- Mobile devices
Problems Solved
This technology addresses the following issues:
- Balancing computation accuracy and energy consumption
- Improving efficiency of artificial neural networks
- Enhancing performance of edge devices
Benefits
The benefits of this technology include:
- Optimized energy consumption
- Improved accuracy in computations
- Enhanced performance of neural networks
Potential Commercial Applications
Optimizing Energy Consumption in Artificial Neural Networks
Unanswered Questions
How does this method compare to existing techniques for balancing computation accuracy and energy consumption in artificial neural networks?
This article does not provide a direct comparison with existing techniques, leaving room for further analysis and evaluation.
What are the potential limitations or drawbacks of implementing this method in practical applications?
The article does not discuss any potential limitations or drawbacks that may arise when implementing this method in real-world scenarios, which could be important considerations for developers and researchers.
Original Abstract Submitted
A method to balance computation accuracy and energy consumption, including: programming thresholds voltages of first memory cells to store first weight matrices representative of a first artificial neural network; programming thresholds voltages of second memory cells to store second weight matrices representative of a second artificial neural network smaller than the first artificial neural network, where both the first artificial neural network and the second artificial neural network are operable to provide at least one common functionality in processing each of the inputs; selecting configurations of using the first memory cells, or the second memory cells, or both in processing a sequence of inputs; and performing, according to the configurations, operations of multiplication and accumulation using the first memory cells, and the second memory cells in computations of the first artificial neural network and the second artificial neural network in processing the sequence of the inputs.
