Machine Learning Augmented Compact Modeling for Simultaneous Improvement in Computational Speed and Accuracy

Sheelvardhan, Kumar; Guglani, Surila; Ehteshamuddin, M.; Roy, Sourajeet; DasGupta, Anirvan

doi:10.1109/ted.2023.3251296

Cited by 10 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The total number of training data points is 1,000×26×8 = 208,000 (I-V model), 1,000×26×3 = 78,000 (C-V model). The BSIM-CMG model in ASAP7 is an analytical low-fidelity device model so that the ANN was designed with a small size because the nonlinearity and complexity of electrical characteristics according to geometric parameters are smaller than those of rigorous high-fidelity models such as TCAD [6]. neurons.…”

Section: Model Integration and Expansionmentioning

confidence: 99%

“…An artificial neural network (ANN) model is used to efficiently predict and analyze nonlinear electrical characteristics according to the process parameters of the device [5]. Due to these advantages, the ANN-based compact model is suitable for iterative design optimizations and parametric analysis because it effectively predicts nonlinear electrical characteristics for geometric, physical, material, and bias parameters [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancement and Expansion of the Neural Network-Based Compact Model Using a Binning Method

Choi,

Jeong,

Woo

et al. 2024

IEEE J. Electron Devices Soc.

View full text Add to dashboard Cite

The artificial neural network (ANN)-based compact model has significant advantages over physics-based standard compact models such as BSIM-CMG because it can achieve higher accuracy over a wide range of geometric parameters. This makes it particularly suitable for design space exploration and optimization. However, the ANN-based compact model using only one set of model parameters (global-ANN) requires larger model sizes to achieve wider coverage and higher accuracy in order to capture the unpredictable nonlinearities of emerging devices. This results in reduced simulation speed and a trade-off between simulation accuracy, model coverage, and simulation speed makes it difficult to utilize ANN-based compact models in a variety of ways. To solve this problem, we propose the first ANN-based compact modeling flow using a binning method (binning-ANN) and we address the training requirements and data sparsity issues that may occur due to the binning method in ANNs. In addition, we develop a bin size optimization guideline for the binning-ANN. As a result, the binning-ANN not only has higher accuracy, but also much better expandability than existing methods.

show abstract

Section: Model Integration and Expansionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enhancement and Expansion of the Neural Network-Based Compact Model Using a Binning Method

Choi,

Jeong,

Woo

et al. 2024

IEEE J. Electron Devices Soc.

View full text Add to dashboard Cite

show abstract

“…Recently, data-based quality management techniques have been applied in various cases, and their utility continues to rise. Among these techniques, machine learning is the most popular approach in fields such as design automation [14], semiconductor analysis [15] and modeling [16]. Especially for classifications, machine learning can be a reliable and scalable solution.…”

Section: Introductionmentioning

confidence: 99%

Classification of LED Packages for Quality Control by Discriminant Analysis, Neural Network and Decision Tree

Shim,

Kim

2024

Micromachines

View full text Add to dashboard Cite

This study investigates supervised learning to improve LED classification. A hardware system for testing was built. The data for learning were acquired and then analyzed to show their characteristics. An LED was tested, and the results were categorized into three defective LED groups and one normal LED group. Before classification, electrical and optical data were examined to identify their characteristics. To find out the best way for quality control, an ensemble of methods was used. First, the discriminant analysis using the validation data achieved a 77.9% true positive rate for normal products, inadequate for quality control. Second, neural network-based learning boosted this rate to 97.8%, but the 2.2% false negative rate remained problematic. Finally, a binary decision tree was constructed, achieving a 99.4% true positive rate from just 14 splits, proving highly effective in product classification. The training time was measured as 8.1, 18.2 and 8.2 s for discriminant analysis, neural network and decision tree, respectively. This work has found the binary decision tree is advantageous considering both learning and classification efficiencies.

show abstract

“…Recently, a study by Sheelvardhan et al [15] highlighted the potential of knowledge-based ML algorithms in overcoming the limitations of traditional ML-based approaches for semiconductor device modeling. By leveraging prior knowledge, these algorithms offer a promising solution to address the complexities associated with establishing and training ML models.…”

mentioning

confidence: 99%

Improving Semiconductor Device Modeling for Electronic Design Automation by Machine Learning Techniques

Wang,

Li,

Leon

et al. 2024

IEEE Trans. Electron Devices

View full text Add to dashboard Cite

The semiconductors industry benefits greatly from the integration of machine learning (ML)-based techniques in technology computer-aided design (TCAD) methods. The performance of ML models, however, relies heavily on the quality and quantity of training datasets. They can be particularly difficult to obtain in the semiconductor industry due to the complexity and expense of the device fabrication. In this article, we propose a self-augmentation strategy for improving ML-based device modeling using variational autoencoder (VAE)-based techniques. These techniques require a small number of experimental data points and do not rely on TCAD tools. To demonstrate the effectiveness of our approach, we apply it to a deep neural network (DNN)-based prediction task for the ohmic resistance value in gallium nitride (GaN) devices. A 70% reduction in mean absolute error (MAE) when predicting experimental results is achieved. The inherent flexibility of our approach allows easy adaptation to various tasks, thus making it highly relevant to many applications of the semiconductor industry.

show abstract

Machine Learning Augmented Compact Modeling for Simultaneous Improvement in Computational Speed and Accuracy

Cited by 10 publications

References 16 publications

Enhancement and Expansion of the Neural Network-Based Compact Model Using a Binning Method

Enhancement and Expansion of the Neural Network-Based Compact Model Using a Binning Method

Classification of LED Packages for Quality Control by Discriminant Analysis, Neural Network and Decision Tree

Improving Semiconductor Device Modeling for Electronic Design Automation by Machine Learning Techniques

Contact Info

Product

Resources

About