Multimodal transistors as ReLU activation functions in physical neural network classifiers

Pesch, Isin Surekcigil; Bestelink, Eva; Sagazan, Olivier de; Mehonić, Adnan; Sporea, Radu A.

doi:10.1038/s41598-021-04614-9

Cited by 16 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, there is a report of a TFT using the two separated gates. Although Pesch et al did not explicitly use the word ‘split-gate’, they introduced the multimodal transistor (MMT), recognized for its energy efficiency and high performance in analog and other mixed-signal applications [ 78 ]. As shown in Figure 3 d, the MMT was controlled by applying gate voltage biasing, as shown in Figure 3 e. Carrier injection and current switching can be independently controlled by two gates.…”

Section: Discussionmentioning

confidence: 99%

“… ( a ) Split-gate FET in FinFET structure with a 35 nm length split-gate gap, ( b ) schematic diagram of carrier injection barrier control according to voltage biasing at the split-gate, ( c ) MNIST test results on a neuromorphic device that operates by inducing charge trapping in the feedback system generated by split-gate device operation according to the number (#) of epochs [ 63 ] (adapted from [ 63 ] with permission from Frontiers Media S.A.). ( d ) Schematic diagram of a multi-modal transistor that operates similarly to a split-gate, ( e ) transfer curve at each gate voltage application condition, ( f ) neuromorphic operation of ReLU function implementation according to gap size adjustment [ 78 ] (adapted from [ 78 ] with permission from Springer Nature). ( g ) Schematic diagram of a split-gate device using ambipolar TMD WSe 2 , ( h ) schematic diagram of neuromorphic operation implemented in a circuit of three transistors using split-gate, ( i ) gate operation in an extended circuit.…”

Section: Discussionmentioning

confidence: 99%

“…(c) MNIST test results on a neuromorphic device that operates by inducing charge trapping in the feedback system generated by split-gate device operation according to the number (#) of epochs [63] (adapted from [63] with permission from Frontiers Media S.A.). (d) Schematic diagram of a multi-modal transistor that operates similarly to a split-gate, (e) transfer curve at each gate voltage application condition, (f) neuromorphic operation of ReLU function implementation according to gap size adjustment [78] (adapted from [78] with permission from Springer Nature).…”

Section: Neuromorphic Devicementioning

confidence: 99%

See 2 more Smart Citations

Split-Gate: Harnessing Gate Modulation Power in Thin-Film Electronics

Lee,

Kim,

Yoo

2024

Micromachines

View full text Add to dashboard Cite

With the increase in electronic devices across various applications, there is rising demand for selective carrier control. The split-gate consists of a gate electrode divided into multiple parts, allowing for the independent biasing of electric fields within the device. This configuration enables the potential formation of both p- and n-channels by injecting holes and electrons owing to the presence of the two gate electrodes. Applying voltage to the split-gate allows for the control of the Fermi level and, consequently, the barrier height in the device. This facilitates band bending in unipolar transistors and allows ambipolar transistors to operate as if unipolar. Moreover, the split-gate serves as a revolutionary tool to modulate the contact resistance by controlling the barrier height. This approach enables the precise control of the device by biasing the partial electric field without limitations on materials, making it adaptable for various applications, as reported in various types of research. However, the gap length between gates can affect the injection of the electric field for the precise control of carriers. Hence, the design of the gap length is a critical element for the split-gate structure. The primary investigation in this review is the introduction of split-gate technology applied in various applications by using diverse materials, the methods for forming the split-gate in each device, and the operational mechanisms under applied voltage conditions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Neuromorphic Devicementioning

confidence: 99%

See 1 more Smart Citation

Split-Gate: Harnessing Gate Modulation Power in Thin-Film Electronics

Lee,

Kim,

Yoo

2024

Micromachines

View full text Add to dashboard Cite

show abstract

“…The actfunction represents the activation function. Our work utilizes the Rectified Linear Unit (ReLU) activation function, a nonlinear activation function ( Pesch et al, 2022 ). The standard backpropagation trains the neural network by comparing the target value with the predicted result and updating the weight of the training pair to minimize the loss function ( Rosenbaum, 2022 ).…”

Section: Proposed Methodology For Diabetes Predictionmentioning

confidence: 99%

An intelligent diabetes classification and perception framework based on ensemble and deep learning method

Waqas Khan,

Iqbal,

Ahmad

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

Sugar in the blood can harm individuals and their vital organs, potentially leading to blindness, renal illness, as well as kidney and heart diseases. Globally, diabetic patients face an average annual mortality rate of 38%. This study employs Chi-square, mutual information, and sequential feature selection (SFS) to choose features for training multiple classifiers. These classifiers include an artificial neural network (ANN), a random forest (RF), a gradient boosting (GB) algorithm, Tab-Net, and a support vector machine (SVM). The goal is to predict the onset of diabetes at an earlier age. The classifier, developed based on the selected features, aims to enable early diagnosis of diabetes. The PIMA and early-risk diabetes datasets serve as test subjects for the developed system. The feature selection technique is then applied to focus on the most important and relevant features for model training. The experiment findings conclude that the ANN exhibited a spectacular performance in terms of accuracy on the PIMA dataset, achieving a remarkable accuracy rate of 99.35%. The second experiment, conducted on the early diabetes risk dataset using selected features, revealed that RF achieved an accuracy of 99.36%. Based on our experimental results, it can be concluded that our suggested method significantly outperformed baseline machine learning algorithms already employed for diabetes prediction on both datasets.

show abstract

“…It's in line with a more general movement that is taking place with digitalization in virtually all industry sectors, one in which more and better machine learning techniques are adopted to enhance operational effectiveness and quality control. (Pesch et al, 2022).…”

Section: Integration With Industrial Processesmentioning

confidence: 99%

Advanced ANN Techniques for Precise Detection and Classification of Welding Defects

Faza Ardan Kusuma,

Muhammad Fatchan,

Ahmad Turmudi Zy

2024

IJIST

View full text Add to dashboard Cite

The implementation of the artificial neural network (ANN) algorithm for detecting and classifying welding defects is detailed in this study. A total of 558 welding workpiece images were processed using techniques such as resizing, auto-orientation, flipping, rotation, and annotation, ultimately expanding the dataset to 1,288 images. Feature extraction identified 24 traits across 12,000 data points, which were then condensed to 5,735 data points for the ANN model. The model employed 100 hidden layers, the ReLU activation function, and the L-BFGS-B solver, running for 200 iterations. The configuration achieved near-perfect results, with metrics such as the area under the curve (AUC), classification accuracy, and F1 score averaging a precision of 0.97. These outcomes demonstrate the ANN model's high efficacy in detecting and classifying welding defects, underscoring its potential application for quality assurance in the welding industry. Further investigation into specific defect types, including porosity, spatter, cracks, and undercuts, could further improve detection accuracy.

show abstract

Multimodal transistors as ReLU activation functions in physical neural network classifiers

Cited by 16 publications

References 27 publications

Split-Gate: Harnessing Gate Modulation Power in Thin-Film Electronics

Split-Gate: Harnessing Gate Modulation Power in Thin-Film Electronics

An intelligent diabetes classification and perception framework based on ensemble and deep learning method

Advanced ANN Techniques for Precise Detection and Classification of Welding Defects

Contact Info

Product

Resources

About