Related Experiment Videos
A Unified Flash Memory Platform for Mode-Adaptive and Robust AI Computation
Dayeon Yu1, Hwiho Hwang1, Byeongchan Oh2
1Division of Materials Science and Engineering and Department of Semiconductor Engineering, Hanyang University, Seoul, South Korea.
Advanced Science (Weinheim, Baden-Wurttemberg, Germany)
|July 21, 2026
Summary
This study introduces a dual-mode computing-in-memory (CIM) accelerator for energy-adaptive artificial intelligence (AI). It enables flexible switching between high-precision and ultra-low-power modes without hardware changes, enhancing AI hardware adaptability.
Area of Science:
- Computer Engineering
- Artificial Intelligence Hardware
Background:
- Existing computing-in-memory (CIM) architectures face limitations in balancing accuracy, energy efficiency, and robustness.
- This inflexibility restricts adaptability to diverse artificial intelligence (AI) workloads.
Purpose of the Study:
- To develop a novel dual-mode CIM accelerator enabling energy-adaptive operation.
- To achieve flexible switching between high-precision and ultra-low-power modes within a single hardware platform.
Main Methods:
- Utilized an AND-type charge-trap flash array.
- Integrated transistor-mode current sensing and capacitor-mode charge sensing within the same device structure.
- Implemented peripheral switching for mode selection without device-level structural modification.
Main Results:
- Demonstrated reliable vector-matrix multiplication and hardware neural network inference.
- Showcased strong tolerance to device and voltage variations.
- Confirmed improved energy efficiency and reduced peripheral overhead through system-level benchmarking.
Conclusions:
- Established a practical and scalable CIM platform for energy-adaptive AI hardware.
- The dual-mode architecture dynamically balances performance and robustness.
- Offers a versatile foundation for next-generation AI systems.
Related Concept Videos
01:23System of Memory
Memory is categorized into three major systems: sensory memory, short-term memory (STM), and long-term memory (LTM). These systems differ in their capacity and the duration for which they can hold information. Sensory memory captures raw sensory input from the environment, holding it for just a few seconds or less. For example, on hearing a brief, loud sound, like a car horn honking, the sound seems to linger in the mind for a moment even after it stops. This is an instance of sensory memory...
01:19Understanding Memory
Memory is the retention of information or experiences over time, facilitated through three main processes: encoding, storage, and retrieval. Encoding is the process of inputting information into the memory system. For instance, when listening to a lecture, watching a play, reading a book, or having a conversation, the brain is actively encoding information. This initial stage involves transforming sensory input into a form that can be processed and stored by the brain. Various factors, such as...
01:16Flashbulb Memory
A flashbulb memory is a highly vivid and detailed memory, often linked to events of significant emotional impact. These memories stand out in contrast to everyday memories due to their clarity and the precision with which they are recalled. The strong emotions associated with the event act as a catalyst, ensuring that specific details, such as one's location, actions, and even peripheral elements, are etched into memory with remarkable accuracy. For example, many people can vividly recall where...
01:22Multi-input and Multi-variable systems
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
In the absence of...
01:26Higher Mental Functions of Brain: Learning and Memory
Memory is one of the most vital higher mental functions of the brain. Memory is closely related to learning because it enables us to retain information and experiences from our past to use them in our present life. It also helps us to remember facts, events, and skills, such as riding a bike or swimming. There are two types of memory — declarative memory, which involves memorizing facts or events, and procedural memory, which enables us to remember how to do something like writing or playing an...
01:21Cognitive Learning
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...