A System for Generating Non-Uniform Random Variates using Graphene Field-Effect Transistors

Tye, Nathaniel Joseph; Meech, James T.; Bilgin, Bilgesu A.; Stanley-Marbell, Phillip

doi:10.1109/asap49362.2020.00026

Cited by 2 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The above significant nonlinear switching coupled with the memory effect can be potentially exploited to enable non‐volatile memory electronics toward the development of neuromorphic hardware and systems for high‐efficiency artificial neural network computing. [ 30 ] However, P(VDF‐TrFE) can suffer from rapid ferroelectric fatigue, [ 26 ] that can lead to the converging of the memory, as we demonstrate with the two‐terminal vertical devices. In the endeavor to develop non‐volatile memory electronics, the memory (i.e., the switching hysteresis) needs to be enhanced.…”

Section: Resultsmentioning

confidence: 68%

Conduction Modulation of Solution‐Processed 2D Materials

Liu,

Fan,

Wen

et al. 2024

Adv Elect Materials

View full text Add to dashboard Cite

Solution‐processed 2D materials hold promise for their scalable applications. However, the random, fragmented nature of the solution‐processed nanoflakes and the poor percolative conduction through their discrete networks limit the performance of the enabled devices. To overcome the problem, conduction modulation of the solution‐processed 2D materials is reported via Stark effect. Using liquid‐phase exfoliated molybdenum disulfide (MoS2) as an example, nonlinear conduction switching with a ratio of >105 is demonstrated by the local fields from the interfacial ferroelectric P(VDF‐TrFE). Through density‐functional theory calculations and in situ Raman scattering and photoluminescence spectroscopic analysis, the modulation is understood to arise from a charge redistribution in the solution‐processed MoS2. Beyond MoS2, the modulation may be shown effective for the other solution‐processed 2D materials and low‐dimensional materials. The modulation can open their electronic device applications, for instance, thin‐film nonlinear electronics and non‐volatile memories.

show abstract

Section: Resultsmentioning

confidence: 68%

Conduction Modulation of Solution‐Processed 2D Materials

Liu,

Fan,

Wen

et al. 2024

Adv Elect Materials

View full text Add to dashboard Cite

show abstract

“…However, this does not preclude the use of GFETs for alternative computing applications. Our own work provides an example of this [172]. Figure 8 provides an illustrated overview of the process.…”

Section: B Case Study: Generating Non-uniform Random Variates With Gfetsmentioning

confidence: 99%

“…Fig.8. Overview of the development process for the GFET-based non-uniform random variate generator in[172], showing the combination of materials and device selection as well as a mapping of a computational problem to an experimental device.…”

mentioning

confidence: 99%

Bridging the Band Gap: What Device Physicists Need to Know About Machine Learning

Tye¹,

Hofmann²,

Stanley-Marbell³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

This article surveys the landscape of semiconductor materials and devices research for the acceleration of machine learning (ML) algorithms. We observe a disconnect between the semiconductor and device physics and engineering communities, and the digital logic and computer hardware architecture communities. The article first provides an overview of the principles of computational complexity and fundamental physical limits to computing and their relation to physical systems.The article then provides an introduction to ML by presenting three key components of ML systems: representation, evaluation, and optimisation. The article then discusses and provides examples of the application of emerging technologies from the semiconductor and device physics domains as solutions to computational problems, alongside a brief overview of emerging materials and devices for computing applications.The article then reviews the landscape of ML accelerators, comparing fixed-function and reprogrammable digital logic with novel devices such as memristors, resistive memories, magnetic memories, and probabilistic bits. We observe broadly lower performance of ML accelerators based on novel devices and materials when compared to those based on digital complimentary metal-oxide semiconductor (CMOS) technology, particularly in the MNIST optical character recognition task, a common ML benchmark, and also highlight the lack of a trend of progress in approaches based on novel materials and devices.Lastly, the article proposes figures of merit for meaningful evaluation and comparison of different ML implementations in the hope of fostering a dialogue between the materials science, device physics, digital logic, and computer architecture communities by providing a common frame of reference for their work.

show abstract

A System for Generating Non-Uniform Random Variates using Graphene Field-Effect Transistors

Cited by 2 publications

References 41 publications

Conduction Modulation of Solution‐Processed 2D Materials

Conduction Modulation of Solution‐Processed 2D Materials

Bridging the Band Gap: What Device Physicists Need to Know About Machine Learning

Contact Info

Product

Resources

About