18063936. NEURAL NETWORK DEVICE AND ELECTRONIC SYSTEM INCLUDING THE SAME simplified abstract (Samsung Electronics Co., Ltd.)
Contents
NEURAL NETWORK DEVICE AND ELECTRONIC SYSTEM INCLUDING THE SAME
Organization Name
Inventor(s)
Seunggeol Nam of Suwon-si (KR)
NEURAL NETWORK DEVICE AND ELECTRONIC SYSTEM INCLUDING THE SAME - A simplified explanation of the abstract
This abstract first appeared for US patent application 18063936 titled 'NEURAL NETWORK DEVICE AND ELECTRONIC SYSTEM INCLUDING THE SAME
Simplified Explanation
The abstract describes a neural network device that consists of multiple word lines, bit lines, and memory cells. Each memory cell contains two or more ferroelectric memories connected in parallel along a word line.
- The neural network device includes word lines, bit lines, and memory cells.
- The word lines extend in one direction, while the bit lines extend in a perpendicular direction.
- The memory cells are located at the intersections of the word lines and bit lines.
- Each memory cell contains multiple ferroelectric memories.
- The ferroelectric memories are connected in parallel along a word line.
Potential Applications:
- Artificial intelligence: The neural network device can be used in AI systems for tasks such as pattern recognition, speech recognition, and natural language processing.
- Data storage: The device's memory cells can be used for storing and retrieving large amounts of data efficiently.
- Robotics: The neural network device can be integrated into robotic systems to enable learning and decision-making capabilities.
Problems Solved:
- Efficient memory access: The parallel connection of ferroelectric memories along a word line allows for faster and more efficient access to stored data.
- Scalability: The arrangement of word lines and bit lines enables the device to be scaled up to accommodate larger neural networks and data storage requirements.
- Reliability: The use of ferroelectric memories provides a reliable and stable storage medium for long-term data retention.
Benefits:
- Improved performance: The parallel connection of ferroelectric memories allows for faster data access and processing, leading to improved overall performance of the neural network device.
- Increased storage capacity: The device's memory cells can store a larger amount of data due to the parallel connection of multiple ferroelectric memories.
- Energy efficiency: The neural network device is designed to consume less power, making it more energy-efficient compared to traditional memory devices.
Original Abstract Submitted
Provided is a neural network device including a plurality of word lines extending in a first direction, a plurality of bit lines extending in a second direction intersecting the first direction, and a plurality of memory cells arranged at points where the plurality of word lines and the plurality of bit lines intersect one another. Each of the plurality of memory cells includes at least two ferroelectric memories connected in parallel along a word line corresponding to each of the plurality of memory cells.
