Integer-Only CNNs with 4 Bit Weights and Bit-Shift Quantization Scales at Full-Precision Accuracy

Vandersteegen, Maarten; Beeck, Kristof Van; Goedemé, Toon

doi:10.3390/electronics10222823

Cited by 10 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To classified the cognitive training trace, three commonly EEG classification models used at present were compared: EEG-Net [33], 4-CNN [34], and EEG-GRUNet [35].…”

Section: Eeg Signal Classification Resultsmentioning

confidence: 99%

Navigation Learning Assessment Using EEG-Based Multi-Time Scale Spatiotemporal Compound Model

Wang,

Liu,

et al. 2024

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

This study presents a novel method to assess the learning effectiveness using Electroencephalography (EEG)-based deep learning model. It is difficult to assess the learning effectiveness of professional courses in cultivating students' ability objectively by questionnaire or other assessment methods. Research in the field of brain has shown that innovation ability can be reflected from cognitive ability which can be embodied by EEG signal features. Three navigation tasks of increasing cognitive difficulty were designed and a total of 41 subjects participated in the experiment. For the classification and tracking of the subjects' EEG signals, a convolutional neural network (CNN)-based Multi-Time Scale Spatiotemporal Compound Model (MTSC) is proposed in this paper to extract and classify the features of the subjects' EEG signals. Furthermore, Spiking neural networks (SNN) -based NeuCube is used to assess the learning effectiveness and demonstrate cognitive processes, acknowledging that NeuCube is an excellent method to display the spatiotemporal differences between spikes emitted by neurons. The results of the classification experiment show that the cognitive training traces of different students in solving three navigational problems can be effectively distinguished. More importantly, new information about navigation is revealed through the analysis of feature vector visualization and model dynamics. This work provides a foundation for future research on cognitive navigation and the training of students' navigational skills.

show abstract

“…To classified the cognitive training trace, three commonly EEG classification models used at present were compared: EEG-Net [33], 4-CNN [34], and EEG-GRUNet [35].…”

Section: Eeg Signal Classification Resultsmentioning

confidence: 99%

Navigation Learning Assessment Using EEG-Based Multi-Time Scale Spatiotemporal Compound Model

Wang,

Liu,

et al. 2024

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…To verify the validity of MTSC, three EEG classification models commonly used at present were compared: EEG-Net [28], 4-CNN [29], and EEG-GRUNet [30]. The experimental samples were input into the three classification models and MTSC.…”

Section: Eeg Signal Classification Resultsmentioning

confidence: 99%

Navigation Learning Assessment Using EEG-based Multi-Time Scale Spatiotemporal Compound Model

Wang¹,

Liu²,

Li³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p> In this paper, Electroencephalography (EEG) from physiological indicators was introduced to the assessment of teaching effectiveness in the higher education. The Multi-Time Scale Spatiotemporal Compound Model (MTSC) was proposed to extract and classify the features of participants’ EEG signals. The presented MTSC objectively elucidated that the Hand on Modular Engineering Project-Based (HMEP-based) navigation course reshapes students’ innovation ability. </p>

show abstract

“…2) Lower-bit Quantization: There are various quantization methods below 8 bits, including 4-bit quantization [118]- [120], 3-bit quantization [121], 2-bit quantization [122], [123], binary network [124]- [126], ternary network [127], [128]. These studies have achieved a very high compression ratio while retaining the performance of the original network as much as possible.…”

Section: B Quantization Of Different Bitsmentioning

confidence: 99%

A Review of AIoT-based Edge Devices and Lightweight Deployment

Sun¹,

Wang²,

Zhao³

2023

Preprint

View full text Add to dashboard Cite

<p>Artificial Intelligence of Things (AIoT) which inte?grates artificial intelligence (AI) and the Internet of Things (IoT), has attracted increasing attention recently. With the remarkable development of AI, deep neural networks (DNNs) have achieved great success from research to deployment in many applications. However, deploying complex and state-of-the-art (SOTA) AI models on edge applications is increasingly a big challenge. This paper focuses on the convergence of AIoT-based edge devices, lightweight DNNs, and neural network compression. We provide a comprehensive analysis of them and many practical suggestions for researchers: how to obtain/design lightweight DNNs, how to select suitable AI edge devices, and how to compress and deploy them in practice. Finally, future trends and opportunities are presented, including trustworthy AI, federated learning, and robust deployment. </p>

show abstract

Integer-Only CNNs with 4 Bit Weights and Bit-Shift Quantization Scales at Full-Precision Accuracy

Cited by 10 publications

References 33 publications

Navigation Learning Assessment Using EEG-Based Multi-Time Scale Spatiotemporal Compound Model

Navigation Learning Assessment Using EEG-Based Multi-Time Scale Spatiotemporal Compound Model

Navigation Learning Assessment Using EEG-based Multi-Time Scale Spatiotemporal Compound Model

A Review of AIoT-based Edge Devices and Lightweight Deployment

Contact Info

Product

Resources

About