Ultrafast machine vision with 2D material neural network image sensors

Mennel, Lukas; Symonowicz, Joanna; Wachter, Stefan; Polyushkin, Dmitry K.; Molina‐Mendoza, Aday J.; Mueller, Thomas

doi:10.1038/s41586-020-2038-x

Cited by 741 publications

(698 citation statements)

References 35 publications

Supporting

Mentioning

694

Contrasting

Unclassified

Order By: Relevance

“…Graphene and related two-dimensional (2D) materials are a family of exciting materials, which are as small as one to three atoms in vertical direction, but extremely large in horizontal space [1][2][3][4][5]. These systems have attracted significant attention for nanoelectronics and optoelectronics [6][7][8][9][10], non-von Neumann architecture computing [11,12], hybrid flexible and stretchable electronics [13][14][15], and many other applications. As a consequence of their extremely high market value, 2D materials are very attractive to many industries.…”

Section: Introductionmentioning

confidence: 99%

RETRACTED: Artificial Intelligence Algorithm Enabled Industrial-Scale Graphene Characterization

2020

View full text Add to dashboard Cite

No characterization method is available to quickly perform quality inspection of 2D materials produced on an industrial scale. This hinders the adoption of 2D materials for product manufacturing in many industries. Here, we report an artificial-intelligence-assisted Raman analysis to quickly probe the quality of centimeter-large graphene samples in a non-destructive manner. Chemical vapor deposition of graphene is devised in this work such that two types of samples were obtained: layer-plus-islands and layer-by-layer graphene films, at centimeter scales. Using these samples, we implemented and integrated an unsupervised learning algorithm with an automated Raman spectroscopy to precisely cluster 20,250 and 18,000 Raman spectra collected from layer-plus-islands and layer-by-layer graphene films, respectively, into five and two clusters. Each cluster represents graphene patches with different layer numbers and stacking orders. For instance, the two clusters detected in layer-by-layer graphene films represent monolayer and bilayer graphene based on their Raman fingerprints. Our intelligent Raman analysis is fully automated, with no human operation involved, is highly reliable (99.95% accuracy), and can be generalized to other 2D materials, paving the way towards industrialization of 2D materials for various applications in the future.

show abstract

Section: Introductionmentioning

confidence: 99%

RETRACTED: Artificial Intelligence Algorithm Enabled Industrial-Scale Graphene Characterization

2020

View full text Add to dashboard Cite

show abstract

“…Machine vision involving both the self-adaptive image sensing and in-sensor computing may enable smart and faithful capturing of the visual information from the environment, as well as offer in situ efficient image-processing capability by avoiding the massive shuttling of abundant data between the sensor and computing units. [20,29] This is critically important for user-end applications wherein the fast responding and decision-making www.advancedsciencenews.com www.advintellsyst.com image sensor during photographing. Therefore, light intensity can be used as input signal of the neural network and intrinsically connects the sensing and computing capability of the present perovskite devices.…”

Section: Resultsmentioning

confidence: 99%

“…[26][27][28] In addition, the externally tuned photoresponsivity of the individual perovskite devices may also act as updatable synaptic weight for machine-learning algorithms and turns the image sensor array into an ANN for real-time processing of the visual information. [29] In this work, we present a ternary cation halide Cs 0.05 FA 0.81 MA 0.14 PbI 2.55 Br 0.45 (CsFAMA)-based perovskite switchable visual sensor that exhibits full-visible-spectra photovoltaic behavior and reconfigurable responsivity for adaptive image sensing and in-sensor machine vision. Experimental results demonstrate that imaging of the target object can be achieved in an adaptive manner by the ion-migration-induced switchable photovoltaic characteristics, whereas the tunable photoresponsivity enable the sensor array as perceptron neural network (PNN) for performing simple instant computation tasks.…”

mentioning

confidence: 99%

Switchable Perovskite Photovoltaic Sensors for Bioinspired Adaptive Machine Vision

Chen

Zhang

Liu

et al. 2020

Advanced Intelligent Systems

View full text Add to dashboard Cite

Machine vision is an indispensable part of today's artificial intelligence. The artificial visual systems used in industrial production and domestic daily life rely significantly on cameras and image‐processing components for live monitoring and target identifying. They, however, often suffer from bulky volume, high energy consumption, and more critically, lack of adaptive responsiveness under extreme lighting conditions and thus possible mortal visual disability of flash blinding or nyctalopia for applications such as auto‐piloting. Herein, it is demonstrated that perovskite switchable photovoltaic devices are used to effectively construct all‐in‐one sensory neural network. Arising from the spontaneous and electric field‐induced ion‐migration effect, the photoresponsivity of the perovskite device can be reconfigured over the wide range of 540–1270%, which not only allows high‐fidelity adaptive image sensing of the visual information but also acts as updatable synaptic weight to enable the sensor array for performing machine‐learning tasks. With the bioinspired electronic pupil regulation function achieved through adjustable photoresponsivity of the perovskite sensor array, a proof‐of‐concept adaptive machine vision system with a maximum 263% enhancement of the object recognition accuracy for compact, mobile yet delay‐sensitive applications is demonstrated.

show abstract

“…One potential scheme to mitigate such system and function disparities could be through designing and printing in-sensor data processing. [1015,[1069][1070][1071] Research in flexible data storage devices has also achieved significant progress. However, the printed memory devices for wearable applications are yet to be reported.…”

Section: Challenges and Opportunitiesmentioning

confidence: 99%

Ink‐Based Additive Nanomanufacturing of Functional Materials for Human‐Integrated Smart Wearables

2020

Advanced Intelligent Systems

View full text Add to dashboard Cite

Human-integrated devices include wearable and implantable devices for monitoring vital human signals or interacting with the human body. [1-3] The human-integrated devices needed to be tethered to the organs or the human skin for implementing their functions such as sensing and energy harvesting. [4-18] The economical, agile, customizable manufacturing, and integration of multifunctional device modules into networked systems with mechanical compliance and robustness will enable unprecedented human-integrated smart wearables [19-23] and usher in exciting opportunities in emerging technologies such as electronics, [24-29] wearable computation, [30-36] human-machine interface, [37-42] robotics, [43-48] and advanced healthcare. [49-54] The fabrication of stateof-the-art microelectronics involves hightemperature processing steps, which are generally incompatible with the flexible substrates (e.g., paper, polymer, fiber, etc.) [55-61] widely used in the wearable devices. Moreover, the current microfabrication technologies are not well positioned to process the emerging functional nanomaterials (e.g., nanowires [NWs] and 2D materials). [62-65] Such incomparability severely limits the pace of deploying these emerging materials (despite their unprecedented properties) in wearable and flexible device technologies. The additive manufacturing (AM) processes have emerged as potential candidates for addressing the earlier limitations of the current microfabrication technologies in fabricating flexible/wearable printed devices with diversified functionalities, e.g., energy harvesting/storage, sensing, actuation, and computation, leveraging advantages such as maskless processing, versatile ink formulation, low cost, low processing temperature, and scalability. [66-71] Researchers have devoted tremendous efforts to develop the related technologies, and several reviews have provided excellent discussions on the material formulation and process aspects of AM techniques. [63,72-79] However, to our best knowledge, there are few review reports about the ink-based additive nanomanufacturing of functional materials for human-integrated smart wearables. To fill this gap, here we review the recent progress in ink-based

show abstract

Ultrafast machine vision with 2D material neural network image sensors

Cited by 741 publications

References 35 publications

RETRACTED: Artificial Intelligence Algorithm Enabled Industrial-Scale Graphene Characterization

RETRACTED: Artificial Intelligence Algorithm Enabled Industrial-Scale Graphene Characterization

Switchable Perovskite Photovoltaic Sensors for Bioinspired Adaptive Machine Vision

Ink‐Based Additive Nanomanufacturing of Functional Materials for Human‐Integrated Smart Wearables

Contact Info

Product

Resources

About