Deep Learning Applied to Computational Mechanics:A Comprehensive Review,State of the Art,and the Classics

Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.

Mammogram Learning System for Breast Cancer Diagnosis Using Deep Learning SVM

The most common form of cancer for women is breast cancer.Recent advances in medical imaging technologies increase the use of digital mammograms to diagnose breast cancer.Thus,an automated computerized system with high accuracy is needed.In this study,an efficient Deep Learning Architecture(DLA)with a Support Vector Machine(SVM)is designed for breast cancer diagnosis.It combines the ideas from DLA with SVM.The state-of-the-art Visual Geometric Group(VGG)architecture with 16 layers is employed in this study as it uses the small size of 3×3 convolution filters that reduces system complexity.The softmax layer in VGG assumes that the training samples belong to exactly only one class,which is not valid in a real situation,such as in medical image diagnosis.To overcome this situation,SVM is employed instead of the softmax layer in VGG.Data augmentation is also employed as DLA usually requires a large number of samples.VGG model with different SVM kernels is built to classify the mammograms.Results show that the VGG-SVM model has good potential for the classification of Mammographic Image Analysis Society(MIAS)database images with an accuracy of 98.67%,sensitivity of 99.32%,and specificity of 98.34%.

Design of a memory polynomial predistorter for wideband envelope tracking amplifiers

Efficiency and linearity of the microwave power amplifier are critical elements for mobile communication systems. A memory polynomial baseband predistorter based on an indirect learning architecture is presented for improving the linearity of an envelope tracing （ET） amplifier with application to a wireless transmitter. To deal with large peak-to-average ratio （PAR） problem, a clipping procedure for the input signal is employed. Then the system performance is verified by simulation results. For a single carrier wideband code division multiple access （WCDMA） signal of 16-quadrature amplitude modulation （16-QAM）, about 2% improvement of the error vector magnitude （EVM） is achieved at an average output power of 45.5 dBm and gain of 10.6 dB, with adjacent channel leakage ratio （ACLR） of -64.55 dBc at offset frequency of 5 MHz. Moreover, a three-carrier WCDMA signal and a third-generation （3G） long term evolution （LTE） signal are used as test signals to demonstrate the performance of the proposed linearization scheme under different bandwidth signals.

Digital Transformation in Teacher Development:Platformization,Ecologization,Practicalization

Based on the analysis of the digital foundation and transformation demands of teacher development,the paper proposes a logical architecture of teachers’digital learning from the perspective of 70-20-10 model for learning and development,including self-learning based on platform resources(10%),blended learning based on collaborative support(20%),and embedded learning based on work scenarios(70%).Then,a pyramid model of evaluation and governance for teacher development needs that is compatible with the three types of learning paradigms is proposed,i.e.,focusing on using teacher portraits to evaluate learning behaviors,using skills certification to evaluate knowledge and competencies,and focusing on ethics to promote practical wisdom.Finally,to support the transformation of learning paradigms plus evaluation and governance,this paper proposes an action architecture of service upgrading for digital transformation in teacher development,namely,creating a multi-level coherent online learning architecture for platformization,creating a seamless learning space with multi-dimensional integration for ecologization,and leading the transformation from just-in-time learning to just-in-need practice for practicalization,ultimately realizing a leap of teachers’practical wisdom.