The effect of weight errors on neural networks

Arechiga, Austin P.; Michaels, Alan J.

doi:10.1109/ccwc.2018.8301749

Cited by 16 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, environmental effects on the hardware must also be considered, in addition to the SWaP requirements required to execute RFML algorithms on varying devices. For example, when deploying RFML algorithms aboard small spacecraft which are impacted by radiation-induced single event upsets [185], [186], without the addition of radiation shielding and/or extensive mitigation strategies, the performance of the ML structures fail to achieve the necessary performance to be practically useful [187]- [192].…”

Section: Application Dependenciesmentioning

confidence: 99%

An RFML Ecosystem: Considerations for the Application of Deep Learning to Spectrum Situational Awareness

Wong

Clark

Flowers

et al. 2021

IEEE Open J. Commun. Soc.

Self Cite

View full text Add to dashboard Cite

While deep learning (DL) technologies are now pervasive in state-of-the-art Computer Vision (CV) and Natural Language Processing (NLP) applications, only in recent years have these technologies started to sufficiently mature in applications related to wireless communications, a field loosely termed Radio Frequency Machine Learning (RFML). In particular, recent research has shown DL to be an enabling technology for Cognitive Radio (CR) applications as well as a useful tool for supplementing expertly defined algorithms for spectrum awareness applications such as signal detection, estimation, and classification. A major driver for the usage of RFML is that little, to no, a priori knowledge of the intended spectral environment is required, given that there is an abundance of representative raw Radio Frequency (RF) data to facilitate training and evaluation. However, in addition to this fundamental need for sufficient data, there are other key considerations, such as trust, security, and hardware requirements, that must be taken into account before deploying RFML systems in real-world wireless communication applications that largely go unaddressed in the current literature. This paper examines the prior works related to these major research considerations, with focus on the dependencies between them and factors unique to the RFML space.

show abstract

Section: Application Dependenciesmentioning

confidence: 99%

An RFML Ecosystem: Considerations for the Application of Deep Learning to Spectrum Situational Awareness

Wong

Clark

Flowers

et al. 2021

IEEE Open J. Commun. Soc.

Self Cite

View full text Add to dashboard Cite

show abstract

“…As described in Sections II and III, the scale and scope of different applications can lead to vastly different hardware and SWaP requirements -at one end of the spectrum a Raspberry Pi 0 for performing event-triggered packet-based SEI for IoT networks [103] and on the other end a real-time 5 GHz instantaneous continuous spectrum monitoring system [2]. One specific application example, driven by environmental effects, is the potential deployment of ML algorithms aboard small spacecraft, which are impacted by radiation-induced single event upsets [254], [255] -without the addition of radiation shielding and/or extensive mitigation strategies, the performance of the ML structures fail to achieve the necessary performance [256]- [261] to be practically useful. Broader dependencies include harnessing the more rapid decision making of RFML -in many applications discussed in Section II, the envisioned use case for RFML is primarily as a decision aid.…”

Section: B Application Dependenciesmentioning

confidence: 99%

The RFML Ecosystem: A Look at the Unique Challenges of Applying Deep Learning to Radio Frequency Applications

Wong,

Clark,

Flowers

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

While deep machine learning technologies are now pervasive in state-of-the-art image recognition and natural language processing applications, only in recent years have these technologies started to sufficiently mature in applications related to wireless communications. In particular, recent research has shown deep machine learning to be an enabling technology for cognitive radio applications as well as a useful tool for supplementing expertly defined algorithms for spectrum sensing applications such as signal detection, estimation, and classification (termed here as Radio Frequency Machine Learning, or RFML). A major driver for the usage of deep machine learning in the context of wireless communications is that little, to no, a priori knowledge of the intended spectral environment is required, given that there is an abundance of representative data to facilitate training and evaluation. However, in addition to this fundamental need for sufficient data, there are other key considerations, such as trust, security, and hardware/software issues, that must be taken into account before deploying deep machine learning systems in real-world wireless communication applications. This paper provides an overview and survey of prior work related to these major research considerations. In particular, we present their unique considerations in the RFML application space, which are not generally present in the image, audio, and/or text application spaces.

show abstract

“…Lee et al [6] investigated circuit errors caused by processing units and proposed partial error masking through dropout to enhance the fault tolerance of neural networks. Austin et al [7] discovered a correlation between weight error and classification accuracy for CNN and MLP. Kwon et al [8] introduced Gaussian noise to the weight parameters of LeNet and observed varying error tolerances among convolutional layers.…”

Section: Introductionmentioning

confidence: 99%

Quantifying the Impact of Single-Event Upsets on Neural Networks with Uncertainty Analysis

Yan,

Gao

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The Convolutional neural networks have gradually penetrated into various fields of social life, in addition to aerospace devices, neural network chips are also indispensable for target recognition and detection, etc. Due to the complex environment in space, neural network chips are extremely easy to be damaged by cosmic rays, so it is urgent to evaluate and enhance the robustness of neural network chips. However, most of the existing researches are monolithic error injection of neural networks and do not build relevant models for quantitative analysis. The goal of this paper is to analyse the effects of single-event upsets (SEUs) induced by the penetration of SRAM storage areas in a quantized neural network chip by energetic particles from space. Firstly, a SEU probability model as well as an uncertainty assessment model are established, and the effect of SEU on the reliability of CNNs is evaluated by fault injection with the upset rate of four chip types. The results of the error injection experiments show that the Virtex-5 type of rollover rate decreases the average accuracy of VGG-16 by 20%, while the other three types of error injection have an impact of about 11% on the accuracy of the neural network. Quantitative experimental results confirm the hypothesis that SEU increases the uncertainty of neural networks. The quantification of these effects contributes to the study of reinforcement of neural network chips.

show abstract

The effect of weight errors on neural networks

Cited by 16 publications

References 10 publications

An RFML Ecosystem: Considerations for the Application of Deep Learning to Spectrum Situational Awareness

An RFML Ecosystem: Considerations for the Application of Deep Learning to Spectrum Situational Awareness

The RFML Ecosystem: A Look at the Unique Challenges of Applying Deep Learning to Radio Frequency Applications

Quantifying the Impact of Single-Event Upsets on Neural Networks with Uncertainty Analysis

Contact Info

Product

Resources

About