This study focuses on exploring the practical path of Micro Project-Based Learning from the perspective of integrated unit teaching,aiming to address the issue of integrating the Project Section with other sections in...This study focuses on exploring the practical path of Micro Project-Based Learning from the perspective of integrated unit teaching,aiming to address the issue of integrating the Project Section with other sections in the new junior high school English textbook published by Shanghai Education Press.Based on two rounds of action research,a micro-project design framework is constructed,which includes“unit micro-project design”,“micro-project-based unit teaching”,“micro-project achievement display”,and“evaluation and reflection”.Practice shows that with the guidance of task lists and scaffolding support,this framework effectively promotes the integration of subject knowledge and the development of students’core competence,providing a transferable implementation paradigm for integrated unit teaching.展开更多
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,particularl...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.展开更多
基于数据驱动的单元测试代码自动化生成技术存在覆盖率低和可读性差的问题,难以应对日益增长的测试需求。大语言模型(LLM)在代码生成任务中显示了极大的潜力,然而由于代码数据的功能风格和编码风格的差异,LLM面临灾难性遗忘和资源受限这...基于数据驱动的单元测试代码自动化生成技术存在覆盖率低和可读性差的问题,难以应对日益增长的测试需求。大语言模型(LLM)在代码生成任务中显示了极大的潜力,然而由于代码数据的功能风格和编码风格的差异,LLM面临灾难性遗忘和资源受限这2个挑战。为了解决这些问题,提出将编码风格和功能风格同步迁移微调的思想,并开发一种高效的LLM微调训练方法用于单元测试用例生成。首先,利用广泛使用的指令数据集对LLM进行指令对齐,并按任务类型对指令集分类;同时,提取并存储具有任务特征的权重增量;其次,设计一个自适应风格提取模块,该模块包含抗噪声干扰学习和编码风格回溯学习,以应对不同的代码编写风格;最后,在目标域分别对功能风格增量和编码风格增量进行联合训练,以实现在目标域低资源情况下的高效适配和微调。在SF110 Corpus of Classes数据集上的测试用例生成实验结果表明,所提方法的结果均优于对比方法,与主流代码生成LLM Codex、Code Llama和DeepSeek-Coder相比,所提方法的编译率分别提高0.8%、43.5%和33.8%、分支覆盖率分别提高3.1%、1.0%和17.2%;行覆盖率分别提高4.1%、6.5%和15.5%,验证了所提方法在代码生成任务上的优越性。展开更多
基金this paper is funded by Project Information:2023 Guangdong Undergraduate Colleges and Universities Teaching Quality and Teaching Reform Project Construction Project,Project Name:Action Research on Whole-area Nurturing of English Reading Teaching in Universities,Secondary and Primary Schools under the Perspective of Discipline Nurturing.Project serial number:895.
文摘This study focuses on exploring the practical path of Micro Project-Based Learning from the perspective of integrated unit teaching,aiming to address the issue of integrating the Project Section with other sections in the new junior high school English textbook published by Shanghai Education Press.Based on two rounds of action research,a micro-project design framework is constructed,which includes“unit micro-project design”,“micro-project-based unit teaching”,“micro-project achievement display”,and“evaluation and reflection”.Practice shows that with the guidance of task lists and scaffolding support,this framework effectively promotes the integration of subject knowledge and the development of students’core competence,providing a transferable implementation paradigm for integrated unit teaching.
文摘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.
文摘基于数据驱动的单元测试代码自动化生成技术存在覆盖率低和可读性差的问题,难以应对日益增长的测试需求。大语言模型(LLM)在代码生成任务中显示了极大的潜力,然而由于代码数据的功能风格和编码风格的差异,LLM面临灾难性遗忘和资源受限这2个挑战。为了解决这些问题,提出将编码风格和功能风格同步迁移微调的思想,并开发一种高效的LLM微调训练方法用于单元测试用例生成。首先,利用广泛使用的指令数据集对LLM进行指令对齐,并按任务类型对指令集分类;同时,提取并存储具有任务特征的权重增量;其次,设计一个自适应风格提取模块,该模块包含抗噪声干扰学习和编码风格回溯学习,以应对不同的代码编写风格;最后,在目标域分别对功能风格增量和编码风格增量进行联合训练,以实现在目标域低资源情况下的高效适配和微调。在SF110 Corpus of Classes数据集上的测试用例生成实验结果表明,所提方法的结果均优于对比方法,与主流代码生成LLM Codex、Code Llama和DeepSeek-Coder相比,所提方法的编译率分别提高0.8%、43.5%和33.8%、分支覆盖率分别提高3.1%、1.0%和17.2%;行覆盖率分别提高4.1%、6.5%和15.5%,验证了所提方法在代码生成任务上的优越性。
