一个基于IGZO光传感器的三元逆变器集成光学传感和重量量化在三元神经网络中的颜色图像识别
Wun-Yun Lin1, Yong-Yi Huang1, Yu-Chieh Chen1
1Department of Materials Science and Engineering, National Cheng Kung University, Tainan, 70101, Taiwan. jenschen@ncku.edu.tw.
Nanoscale horizons
|January 30, 2026
概括
我们使用--氧化薄膜光传感器开发了高效的三元神经网络 (TNN). 这种集成硬件在图像识别方面达到90%以上的准确性,使得边缘AI部署成为可能.
科学领域:
- 材料科学 材料科学 材料科学
- 计算机工程 计算机工程
- 人工智能的人工智能
背景情况:
- 深度神经网络 (DNN) 面临着大型模型大小和计算需求的挑战,限制了边缘部署.
- 三级神经网络 (TNN) 通过每重比特使用更少的比特,为传统DNN提供了更有效的替代方案.
- ---氧化物 (IGZO) 薄膜光晶体管 (TFPTs) 正在探索它们在新型电子应用中的潜力.
研究的目的:
- 开发适合边缘计算的TNN高效硬件实现.
- 使用IGZO TFPTs创建一个紧的三元电路,用于图像识别任务.
- 将光学传感,数据预处理和TNN推断集成到单个硬件模块中.
主要方法:
- 使用两个平行IGZO TFPT和一个电阻设计了一个三元电路,创建了三个离散电流状态 (-1, 0, 1).
- 使用两个IGZO TFPT和两个电阻实现了一个紧的三元逆变器,绕过了复杂的二元CMOS逻辑.
- 光学传感捕获光功率密度和波长,然后将它们分离成TNN输入的像素值.
主要成果:
- 基于IGZO TFPT的电路成功模拟了三个稳定的电流状态的三元逻辑.
- 一个集成的硬件模块证明了有效的数据离散,转换和推断.
- 在用于图像识别任务的CIFAR-10数据集上实现了>90%的准确性.
结论:
- 该研究验证了使用IGZO TFPTs的设备级数据离散和转换的可行性.
- 开发的硬件模块代表了向边缘AI的高效,集成的神经形态视觉系统迈出的重要一步.
- 这种方法解决了DNN的效率限制,为更广泛的边缘AI应用铺平了道路.
相关概念视频
Inverting and Non-inverting OpAmps
1.8K
In an inverting amplifier, the input voltage is connected through a resistor to the inverting terminal. Meanwhile, the non-inverting terminal is grounded and a feedback resistor is established between the inverting and output terminal, as depicted in Figure 1.
1.8K
The Sense of Self: Reflected Self-Appraisal and Social Comparison
56.1K
According to Charles Cooley, we base our image on what we think other people see (Cooley 1902). We imagine how we must appear to others, then react to this speculation. We don certain clothes, prepare our hair in a particular manner, wear makeup, use cologne, and the like—all with the notion that our presentation of ourselves is going to affect how others perceive us. We expect a certain reaction, and, if lucky, we get the one we desire and feel good about it. But more than that, Cooley...
56.1K
Colors and Magnetism
14.1K
Color in Coordination Complexes
When atoms or molecules absorb light at the proper frequency, their electrons are excited to higher-energy orbitals. For many main group atoms and molecules, the absorbed photons are in the ultraviolet range of the electromagnetic spectrum, which cannot be detected by the human eye. For coordination compounds, the energy difference between the d orbitals often allows photons in the visible range to be absorbed and emitted, which is seen as colors by the human...
When atoms or molecules absorb light at the proper frequency, their electrons are excited to higher-energy orbitals. For many main group atoms and molecules, the absorbed photons are in the ultraviolet range of the electromagnetic spectrum, which cannot be detected by the human eye. For coordination compounds, the energy difference between the d orbitals often allows photons in the visible range to be absorbed and emitted, which is seen as colors by the human...
14.1K
Color Vision
1.5K
Color perception begins in the retina, the light-sensitive layer at the back of the eye. Two main theories explain how colors are seen: the trichromatic theory and the opponent-process theory. The trichromatic theory, proposed by Thomas Young in 1802 and extended by Hermann von Helmholtz in 1852, suggests that color vision is based on three types of cone receptors in the retina. These cones are sensitive to different but overlapping ranges of wavelengths corresponding to red, blue, and green.
1.5K
Weighted Mean
6.3K
While taking the arithmetic, geometric, or harmonic mean of a sample data set, equal importance is assigned to all the data points. However, all the values may not always be equally important in some data sets. An intrinsic bias might make it more important to give more weightage to specific values over others.
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
6.3K
Protein Networks
4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K


