17830004. DEVICE WITH NEURAL NETWORK simplified abstract (Samsung Electronics Co., Ltd.)
Contents
DEVICE WITH NEURAL NETWORK
Organization Name
Inventor(s)
Jung-Hoon Chun of Suwon-si, (KR)
Yoonmyung Lee of Suwon-si, (KR)
DEVICE WITH NEURAL NETWORK - A simplified explanation of the abstract
This abstract first appeared for US patent application 17830004 titled 'DEVICE WITH NEURAL NETWORK
Simplified Explanation
The abstract describes a device with a neural network that includes a synaptic memory cell, a reference memory cell, and an output circuit. Here are the key points:
- The device includes a synaptic memory cell with a resistive memory element that generates a column signal based on the resistive memory element and an input signal.
- A reference memory cell is also included, which has a reference memory element with a different resistance value than the resistive memory element in the synaptic memory cell. It generates a reference signal based on the reference memory element and the input signal.
- An output circuit is configured to generate an output signal for the output line using the column signal and the reference signal.
Potential applications of this technology:
- Artificial intelligence: This device can be used in AI systems to enhance the learning and decision-making capabilities of neural networks.
- Pattern recognition: The neural network device can be applied in pattern recognition tasks, such as image or speech recognition, to improve accuracy and efficiency.
- Data analysis: The device can be used in data analysis applications to process and analyze large datasets more effectively.
Problems solved by this technology:
- Improved memory performance: The use of resistive memory elements in the synaptic memory cell and reference memory cell can enhance the memory capabilities of the device, allowing for more efficient data processing.
- Enhanced neural network functionality: The device's neural network architecture, including the synaptic and reference memory cells, can improve the performance and accuracy of neural networks in various applications.
Benefits of this technology:
- Faster processing: The device's neural network architecture enables faster processing of input signals, leading to quicker decision-making and analysis.
- Higher accuracy: The use of resistive memory elements and the neural network's structure can enhance the accuracy of pattern recognition and data analysis tasks.
- Energy efficiency: The device's design and architecture can contribute to energy efficiency, making it suitable for applications where power consumption is a concern.
Original Abstract Submitted
A device with a neural network includes: a synaptic memory cell comprising a resistive memory element, which is disposed along an output line and which has either one of a first resistance value and a second resistance value, and configured to generate a column signal based on the resistive memory element and an input signal in response to the input signal being received through an input line; a reference memory cell comprising a reference memory element, which is disposed along a reference line and which has the second resistance value different from the first resistance value, and configured to generate a reference signal based on the reference memory element and the input signal; and an output circuit configured to generate an output signal for the output line from the column signal and the reference signal.
