Machine Learning to Promote Efficient Screening of Low-Contact Electrode for 2D Semiconductor Transistor Under Limited Data

Low-barrier and high-injection electrodes are crucial for high-performance (HP) 2D semiconductor devices. Conventional trial-and-error methodologies for electrode material screening are impractical because of their low efficiency and arbitrary specificity. Although machine learning has emerged as a promising alternative to tackle this problem, its practical application in semiconductor devices is hindered by its substantial data requirements. In this paper, a comprehensive scheme combining an autoencoding regularized adversarial neural network and a feature-adaptive variational active learning algorithm for screening low-contact electrode materials for 2D semiconductor transistors with limited data is proposed. The proposed scheme exhibits exceptional performance by training with only 15% of the total data points, where the mean square errors are 0.17 and 0.27 eV for the vertical and lateral Schottky barrier, respectively, and 2.88% for tunneling probability. Further, it exhibits an optimal predictive performance for 100 randomly sampled training datasets, reveals the underlying physical insight based on the identified features, and realizes continual improvement by employing detailed density-of-states descriptors. Finally, the empirical evaluations of the transport characteristics are conducted and verified by constructing MOSFET devices. These findings demonstrate the considerable potential of machine-learning techniques for screening high-efficiency electrode materials and constructing HP 2D semiconductor devices.

Prompt-Based Tuning of Transformer Models for Multi-Center Medical Image Segmentation of Head and Neck Cancer

Medical image segmentation is a vital healthcare endeavor requiring precise and efficient models for appropriate diagnosis and treatment. Vision transformer (ViT)-based segmentation models have shown great performance in accomplishing this task. However, to build a powerful backbone, the self-attention block of ViT requires large-scale pre-training data. The present method of modifying pre-trained models entails updating all or some of the backbone parameters. This paper proposes a novel fine-tuning strategy for adapting a pretrained transformer-based segmentation model on data from a new medical center. This method introduces a small number of learnable parameters, termed prompts, into the input space (less than 1% of model parameters) while keeping the rest of the model parameters frozen. Extensive studies employing data from new unseen medical centers show that the prompt-based fine-tuning of medical segmentation models provides excellent performance regarding the new-center data with a negligible drop regarding the old centers. Additionally, our strategy delivers great accuracy with minimum re-training on new-center data, significantly decreasing the computational and time costs of fine-tuning pre-trained models. Our source code will be made publicly available.

Brickognize: Applying Photo-Realistic Image Synthesis for Lego Bricks Recognition with Limited Data

During the last few years, supervised deep convolutional neural networks have become the state-of-the-art for image recognition tasks. Nevertheless, their performance is severely linked to the amount and quality of the training data. Acquiring and labeling data is a major challenge that limits their expansion to new applications, especially with limited data. Recognition of Lego bricks is a clear example of a real-world deep learning application that has been limited by the difficulties associated with data gathering and training. In this work, photo-realistic image synthesis and few-shot fine-tuning are proposed to overcome limited data in the context of Lego bricks recognition. Using synthetic images and a limited set of 20 real-world images from a controlled environment, the proposed system is evaluated on controlled and uncontrolled real-world testing datasets. Results show the good performance of the synthetically generated data and how limited data from a controlled domain can be successfully used for the few-shot fine-tuning of the synthetic training without a perceptible narrowing of its domain. Obtained results reach an AP50 value of 91.33% for uncontrolled scenarios and 98.7% for controlled ones.

Intraclass Image Augmentation for Defect Detection Using Generative Adversarial Neural Networks

Surface defect identification based on computer vision algorithms often leads to inadequate generalization ability due to large intraclass variation. Diversity in lighting conditions, noise components, defect size, shape, and position make the problem challenging. To solve the problem, this paper develops a pixel-level image augmentation method that is based on image-to-image translation with generative adversarial neural networks (GANs) conditioned on fine-grained labels. The GAN model proposed in this work, referred to as Magna-Defect-GAN, is capable of taking control of the image generation process and producing image samples that are highly realistic in terms of variations. Firstly, the surface defect dataset based on the magnetic particle inspection (MPI) method is acquired in a controlled environment. Then, the Magna-Defect-GAN model is trained, and new synthetic image samples with large intraclass variations are generated. These synthetic image samples artificially inflate the training dataset size in terms of intraclass diversity. Finally, the enlarged dataset is used to train a defect identification model. Experimental results demonstrate that the Magna-Defect-GAN model can generate realistic and high-resolution surface defect images up to the resolution of 512 × 512 in a controlled manner. We also show that this augmentation method can boost accuracy and be easily adapted to any other surface defect identification models.

A Siamese Vision Transformer for Bearings Fault Diagnosis

Fault diagnosis methods based on deep learning have progressed greatly in recent years. However, the limited training data and complex work conditions still restrict the application of these intelligent methods. This paper proposes an intelligent bearing fault diagnosis method, i.e., Siamese Vision Transformer, suiting limited training data and complex work conditions. The Siamese Vision Transformer, combining Siamese network and Vision Transformer, is designed to efficiently extract the feature vectors of input samples in high-level space and complete the classification of the fault. In addition, a new loss function combining the Kullback-Liebler divergence both directions is proposed to improve the performance of the proposed model. Furthermore, a new training strategy termed random mask is designed to enhance input data diversity. A comparative test is conducted on the Case Western Reserve University bearing dataset and Paderborn dataset and our method achieves reasonably high accuracy with limited data and satisfactory generation capability for cross-domain tasks.

Analysis of Variability of Functionals of Recombinant Protein Production Trajectories Based on Limited Data

Making statistical inference on quantities defining various characteristics of a temporally measured biochemical process and analyzing its variability across different experimental conditions is a core challenge in various branches of science. This problem is particularly difficult when the amount of data that can be collected is limited in terms of both the number of replicates and the number of time points per process trajectory. We propose a method for analyzing the variability of smooth functionals of the growth or production trajectories associated with such processes across different experimental conditions. Our modeling approach is based on a spline representation of the mean trajectories. We also develop a bootstrap-based inference procedure for the parameters while accounting for possible multiple comparisons. This methodology is applied to study two types of quantities—the “time to harvest” and “maximal productivity”—in the context of an experiment on the production of recombinant proteins. We complement the findings with extensive numerical experiments comparing the effectiveness of different types of bootstrap procedures for various tests of hypotheses. These numerical experiments convincingly demonstrate that the proposed method yields reliable inference on complex characteristics of the processes even in a data-limited environment where more traditional methods for statistical inference are typically not reliable.

Discretization of Learned NETT Regularization for Solving Inverse Problems

Deep learning based reconstruction methods deliver outstanding results for solving inverse problems and are therefore becoming increasingly important. A recently invented class of learning-based reconstruction methods is the so-called NETT (for Network Tikhonov Regularization), which contains a trained neural network as regularizer in generalized Tikhonov regularization. The existing analysis of NETT considers fixed operators and fixed regularizers and analyzes the convergence as the noise level in the data approaches zero. In this paper, we extend the frameworks and analysis considerably to reflect various practical aspects and take into account discretization of the data space, the solution space, the forward operator and the neural network defining the regularizer. We show the asymptotic convergence of the discretized NETT approach for decreasing noise levels and discretization errors. Additionally, we derive convergence rates and present numerical results for a limited data problem in photoacoustic tomography.

A Probabilistic Approach to Explore Signal Execution Mechanisms With Limited Experimental Data

Mathematical models of biochemical reaction networks are central to the study of dynamic cellular processes and hypothesis generation that informs experimentation and validation. Unfortunately, model parameters are often not available and sparse experimental data leads to challenges in model calibration and parameter estimation. This can in turn lead to unreliable mechanistic interpretations of experimental data and the generation of poorly conceived hypotheses for experimental validation. To address this challenge, we evaluate whether a Bayesian-inspired probability-based approach, that relies on expected values for quantities of interest calculated from available information regarding the reaction network topology and parameters can be used to qualitatively explore hypothetical biochemical network execution mechanisms in the context of limited available data. We test our approach on a model of extrinsic apoptosis execution to identify preferred signal execution modes across varying conditions. Apoptosis signal processing can take place either through a mitochondria independent (Type I) mode or a mitochondria dependent (Type II) mode. We first show that in silico knockouts, represented by model subnetworks, successfully identify the most likely execution mode for specific concentrations of key molecular regulators. We then show that changes in molecular regulator concentrations alter the overall reaction flux through the network by shifting the primary route of signal flow between the direct caspase and mitochondrial pathways. Our work thus demonstrates that probabilistic approaches can be used to explore the qualitative dynamic behavior of model biochemical systems even with missing or sparse data.

Production of Low Cost Carbon-Fiber through Energy Optimization of Stabilization Process

To produce high quality and low cost carbon fiber-based composites, the optimization of the production process of carbon fiber and its properties is one of the main keys. The stabilization process is the most important step in carbon fiber production that consumes a large amount of energy and its optimization can reduce the cost to a large extent. In this study, two intelligent optimization techniques, namely Support Vector Regression (SVR) and Artificial Neural Network (ANN), were studied and compared, with a limited dataset obtained to predict physical property (density) of oxidative stabilized PAN fiber (OPF) in the second zone of a stabilization oven within a carbon fiber production line. The results were then used to optimize the energy consumption in the process. The case study can be beneficial to chemical industries involving carbon fiber manufacturing, for assessing and optimizing different stabilization process conditions at large.

Stochastic Proximal Gradient Algorithms for Multi-Source Quantitative Photoacoustic Tomography

The development of accurate and efficient image reconstruction algorithms is a central aspect of quantitative photoacoustic tomography (QPAT). In this paper, we address this issues for multi-source QPAT using the radiative transfer equation (RTE) as accurate model for light transport. The tissue parameters are jointly reconstructed from the acoustical data measured for each of the applied sources. We develop stochastic proximal gradient methods for multi-source QPAT, which are more efficient than standard proximal gradient methods in which a single iterative update has complexity proportional to the number applies sources. Additionally, we introduce a completely new formulation of QPAT as multilinear (MULL) inverse problem which avoids explicitly solving the RTE. The MULL formulation of QPAT is again addressed with stochastic proximal gradient methods. Numerical results for both approaches are presented. Besides the introduction of stochastic proximal gradient algorithms to QPAT, we consider the new MULL formulation of QPAT as main contribution of this paper.