17718612. WEIGHT CONFIRMATION METHOD FOR AN ANALOG SYNAPTIC DEVICE OF AN ARTIFICIAL NEURAL NETWORK simplified abstract (KIA CORPORATION)
WEIGHT CONFIRMATION METHOD FOR AN ANALOG SYNAPTIC DEVICE OF AN ARTIFICIAL NEURAL NETWORK
Organization Name
Inventor(s)
Joon-Hyun Kwon of Hwaseong-si (KR)
Woo-Seok Choi of Hanam-si (KR)
WEIGHT CONFIRMATION METHOD FOR AN ANALOG SYNAPTIC DEVICE OF AN ARTIFICIAL NEURAL NETWORK - A simplified explanation of the abstract
This abstract first appeared for US patent application 17718612 titled 'WEIGHT CONFIRMATION METHOD FOR AN ANALOG SYNAPTIC DEVICE OF AN ARTIFICIAL NEURAL NETWORK
Simplified Explanation
The abstract describes a weight confirmation method for analog synaptic devices in an artificial neural network. The method involves learning the artificial neural network hardware using analog memory devices and a learning algorithm. After the learning process, the total weight of a pair of synaptic devices is read and compared with 0. Weights are then applied to the positive and negative synaptic devices of the pair, and the total weight is confirmed based on these individual weights. This method helps overcome the retention problem of analog synaptic devices, ensuring stable operation of the artificial neural network.
- The method involves learning artificial neural network hardware using analog memory devices and a learning algorithm.
- After learning, the total weight of a pair of synaptic devices is read and compared with 0.
- Weights are applied to the positive and negative synaptic devices of the pair.
- The total weight of the pair is confirmed based on the individual weights.
- This method helps overcome the retention problem of analog synaptic devices.
- It ensures stable operation of the artificial neural network.
Potential Applications
- Artificial intelligence systems
- Machine learning algorithms
- Neural network hardware
Problems Solved
- Overcoming the retention problem of analog synaptic devices
- Ensuring stable operation of artificial neural networks
Benefits
- Improved performance and reliability of artificial neural networks
- Enhanced accuracy and efficiency of machine learning algorithms
- Potential for advancements in artificial intelligence technology
Original Abstract Submitted
A weight confirmation method for analog synaptic devices of an artificial neural network includes: learning artificial neural network hardware based on artificial analog memory devices using an artificial neural network learning algorithm; after the learning of the artificial neural network hardware, reading a total weight of a pair of synaptic devices; comparing the total weight of the pair of synaptic devices with 0; applying weights to a positive synaptic device and a negative synaptic device of the pair of synaptic devices, respectively; and confirming the total weight of the pair of synaptic devices in accordance with the weight of the positive synaptic device and the weight of the negative synaptic device. A retention problem of analog synaptic devices is overcome and thus the artificial neural network may stably operate.
