Related papers: iPad Screencasts as Evidence of Accountable Discip…

Knowledge distillation (KD) is an effective technique to transfer knowledge from one neural network (teacher) to another (student), thus improving the performance of the student. To make the student better mimic the behavior of the teacher,…

Knowledge Distillation (KD) could transfer the ``dark knowledge" of a well-performed yet large neural network to a weaker but lightweight one. From the view of output logits and softened probabilities, this paper goes deeper into the dark…

Knowledge tracing (KT) is a fundamental task in educational data mining that mainly focuses on students' dynamic cognitive states of skills. The question-answering process of students can be regarded as a thinking process that considers the…

We present an iterative active constraint learning (ACL) algorithm, within the learning from demonstrations (LfD) paradigm, which intelligently solicits informative demonstration trajectories for inferring an unknown constraint in the…

Computational thinking has been a recent focus of education research within the sciences. However, there is a dearth of scholarly literature on how best to teach and to assess this topic, especially in disciplinary science courses. Physics…

Compared to traditional learning from scratch, knowledge distillation sometimes makes the DNN achieve superior performance. This paper provides a new perspective to explain the success of knowledge distillation, i.e., quantifying knowledge…

Knowledge distillation (KD) involves transferring knowledge from a pre-trained heavy teacher model to a lighter student model, thereby reducing the inference cost while maintaining comparable effectiveness. Prior KD techniques typically…

A novel Learning-by-Education Node Community framework (LENC) for Collaborative Knowledge Distillation (CKD) is presented, which facilitates continual collective learning through effective knowledge exchanges among diverse deployed Deep…

Artificial intelligence (AI) is reshaping higher education, yet current debates often feel tangled, mixing concerns about pedagogy, operations, curriculum, and the future of work without a shared framework. This paper offers a first attempt…

Knowledge Distillation is a technique which aims to utilize dark knowledge to compress and transfer information from a vast, well-trained neural network (teacher model) to a smaller, less capable neural network (student model) with improved…

Many recent breakthroughs in machine learning have been enabled by the pre-trained foundation models. By scaling up model parameters, training data, and computation resources, foundation models have significantly advanced the…

Students acquire knowledge as they interact with a variety of learning materials, such as video lectures, problems, and discussions. Modeling student knowledge at each point during their learning period and understanding the contribution of…

The recent work of Clark et al. introduces the AI2 Reasoning Challenge (ARC) and the associated ARC dataset that partitions open domain, complex science questions into an Easy Set and a Challenge Set. That paper includes an analysis of 100…

Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distillation (KD) has emerged as an effective strategy to improve…

Most existing distillation methods ignore the flexible role of the temperature in the loss function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In general, the temperature controls the discrepancy…

Artificial intelligence (AI) algorithms have emerged in the educational domain as a tool to make learning more efficient. Different applications for mastering particular skills, learning new languages, and tracking their progress are used…

Knowledge distillation (KD) is essentially a process of transferring a teacher model's behavior, e.g., network response, to a student model. The network response serves as additional supervision to formulate the machine domain, which uses…

Knowledge distillation (KD) is a successful approach for deep neural network acceleration, with which a compact network (student) is trained by mimicking the softmax output of a pre-trained high-capacity network (teacher). In tradition, KD…

This paper considers the problem of evaluating clusterings of very large populations of items. Given two clusterings, namely a Baseline clustering and an Experiment clustering, the tasks are twofold: 1) characterize their differences, and…

We propose and define the construct, cross-disciplinary learning, which can guide learning and assessment in programs that feature sequential learning across multiple STEM disciplines. Cross-disciplinary learning combines insights from…