Related papers: Tinker or Transfer? A Tale of Two Techniques in Te…

It is perhaps not so baffling that we have the ability to develop, refine, and manifest a creative idea, once it has been conceived. But what sort of a system could spawn the initial seed of creativity from which an idea grows? This paper…

Numerous recent techniques for text style transfer characterize their approaches as variants of reinforcement learning and preference optimization. In this work, we consider the relationship between these approaches and a class of…

This paper examines the integration of STEAM (Science, Technology, Engineering, Arts, and Mathematics) into education, emphasizing the inclusion of the Arts to foster creativity alongside traditional STEM skills. STEAM encourages…

In this paper, we study the Tiered Reinforcement Learning setting, a parallel transfer learning framework, where the goal is to transfer knowledge from the low-tier (source) task to the high-tier (target) task to reduce the exploration risk…

Image virtual try-on aims to fit a garment image (target clothes) to a person image. Prior methods are heavily based on human parsing. However, slightly-wrong segmentation results would lead to unrealistic try-on images with large…

We provide visualizations of individual neurons of a deep image recognition network during the temporal process of transfer learning. These visualizations qualitatively demonstrate various novel properties of the transfer learning process…

Syllabus is essentially a concise outline of a course of study, and conventionally a text document. In the past few decades, however, two novel variations of syllabus have emerged, namely "the Graphic Syllabus" and "the Interactive…

Inspiration plays an important role in design, yet its specific impact on data visualization design practice remains underexplored. This study investigates how professional visualization designers perceive and use inspiration in their…

As several critical issues in computing such as algorithmic bias, discriminatory practices, and techno-solutionism have become more visible, numerous efforts are being proposed to integrate criticality in K-16 computing education. Yet, how…

Conventional transfer learning leverages weights of pre-trained networks, but mandates the need for similar neural architectures. Alternatively, knowledge distillation can transfer knowledge between heterogeneous networks but often requires…

Despite the large body of research showing that students in STEM classes at all levels learn better via active learning than they do via lecture, post-secondary physics and astronomy (P&A) faculty members continue to primarily use…

When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…

The development of a workshop using the language, techniques, and processes of visual art to introduce particle physics concepts is described. Innovative delivery methods committed to the interaction and collaboration of different…

Imitation learning is an approach in which an agent learns how to execute a task by trying to mimic how one or more teachers perform it. This learning approach offers a compromise between the time it takes to learn a new task and the effort…

ICT or Information and Communication Technology has pervaded the fields of education.In recent years the term e-learning has emerged as a result of the integration of ICT in the education fields. Following the application this technology…

Active methodologies aim to develop a critical sense of what is learned, relating theoretical concepts to the practical environment. In this work, we propose an active teaching-learning methodology for laboratory classes in which the…

In the context of a classroom lesson, concepts must be visualized and organized in many ways depending on the needs of the teacher and students. Traditional presentation media such as the blackboard or electronic whiteboard allow for static…

This study, conducted among more than 250 physics and chemistry teachers in Morocco, analyzes the impact of experimentation on student learning and attention in middle and high school. The results show that the majority of teachers favor…

Driven by the goal to enable sleep apnea monitoring and machine learning-based detection at home with small mobile devices, we investigate whether interpretation-based indirect knowledge transfer can be used to create classifiers with…

Recent neural implicit representations (NIRs) have achieved great success in the tasks of 3D reconstruction and novel view synthesis. However, they require the images of a scene from different camera views to be available for one-time…