Designing Activities to Teach Higher-Order Skills: How Feedback and Constraint Affect Learning of Experimental Design

The arrival of Generative Artificial Intelligence (GenAI) into higher education has brought about significant transformations in assessment practices and pedagogical approaches. Large Language Models (LLMs) powered by GenAI present unprecedented opportunities for personalised learning journeys. However, the emergence of GenAI in higher education raises concerns regarding academic integrity and the development of essential cognitive and creative skills among students. Critics worry about the potential decline in academic standards and the perpetuation of biases inherent in the training sets used for LLMs. Addressing these concerns requires clear frameworks and continual evaluation and updating of assessment practices to leverage GenAI's capabilities while preserving academic integrity. Here, we evaluated the integration of GenAI into a year-long MSc program to enhance student understanding and confidence in using GenAI. Approaching GenAI as a digital competency, its use was integrated into core skills modules across two semesters, focusing on ethical considerations, prompt engineering, and tool usage. The assessment tasks were redesigned to incorporate GenAI, which takes a process-based assessment approach. Students' perceptions were evaluated alongside skills audits, and they reported increased confidence in using GenAI. Thematic analysis of one-to-one interviews revealed a cyclical relationship between students' usage of GenAI, experience, ethical considerations, and learning adaptation.

show abstract

Multichannel Wavelet Kernel Network for High Dimensional Inverse Modeling of Microwave Filters

Zhang,

Zhou,

Wang

et al. 2024

Electronics

View full text Add to dashboard Cite

This paper proposes a multichannel wavelet kernel network (MWKN) modeling technique with a two-stage training technique for high-dimensional inverse modeling of microwave filters. The real and imaginary parts of the transmission and reflection characteristics are used as the model inputs, while the geometric parameters of the filter are designated as the outputs. Since the electrical signal in microwave inverse modeling encompasses multiple frequency components and complex information arising from the subtle dimensional changes in the metal pattern, the wavelet transform is introduced by leveraging its powerful multi-scale and approximate detail features to form the discrete wavelet convolution layer in the proposed MWKN. To adapt to the learning of approximate detailed features at different scales, the learnable parameters of this layer and the weights of the backbone network are adjusted in stages through a two-stage training strategy based on particle swarm optimization (PSO), which jointly promotes the rapid convergence of the model. Three numerical examples demonstrate the effectiveness and robustness of the proposed MWKN model. Compared with the traditional design method using electromagnetic (EM) simulation, this approach significantly and substantially reduces the repeated calculation time and is capable of predicting the geometry that meets the design specifications within 0.42 s.

show abstract

Designing Activities to Teach Higher-Order Skills: How Feedback and Constraint Affect Learning of Experimental Design

Cited by 3 publications

References 49 publications

Advanced electromagnetic modeling method based on neuro-space mapping for SISL devices

Advanced electromagnetic modeling method based on neuro-space mapping for SISL devices

Embedding Generative AI as a digital capability into a year-long MSc skills program

Multichannel Wavelet Kernel Network for High Dimensional Inverse Modeling of Microwave Filters

Contact Info

Product

Resources

About