Related papers: Secret objectives: promoting inquiry and tackling …

Concept embeddings offer a practical and efficient mechanism for injecting commonsense knowledge into downstream tasks. Their core purpose is often not to predict the commonsense properties of concepts themselves, but rather to identify…

With the advent of research-grade robotic telescopes (and professional archives) coupled with the wide availability of the Internet in schools, getting high-quality data in the classroom has become much easier than ever before. Robotic…

Deep learning often requires the manual collection and annotation of a training set. On robotic platforms, can we partially automate this task by training the robot to be curious, i.e., to seek out beneficial training information in the…

Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive…

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Sliding friction is usually introduced in high school, but rarely through activities in laboratory. A qualitative introduction to friction is presented by proposing exploration of different kind of materials in order to suggest which…

This paper explores the pedagogical potential of "teacher pre-prompting" as a means of guiding student collaboration in programming education. In particular, we investigate how brief teacher-initiated questions posed before students engage…

Students interactions while solving problems in learning environments (i.e. log data) are often used to support students learning. For example, researchers use log data to develop systems that can provide students with personalized problem…

Subjective tests are the gold standard for evaluating speech quality and intelligibility; however, they are time-consuming and expensive. Thus, objective measures that align with human perceptions are crucial. This study evaluates the…

Opacity is a confidentiality property that holds when certain secret strings of a given system cannot be revealed to an outside observer under any system activity. Opacity violations stimulate the study of opacity enforcement strategies.…

A PhD student is locked inside a box, imitating a quantum system by mimicking the measurement statistics of any viable observable nominated by external observers. Inside a second box lies a genuine quantum system. Either box can be used to…

An active learner is given a hypothesis class, a large set of unlabeled examples and the ability to interactively query labels to an oracle of a subset of these examples; the goal of the learner is to learn a hypothesis in the class that…

Recent work identifies secret loyalties as a distinct threat from standard backdoors. A secret loyalty causes a model to covertly advance the interests of a specific principal while appearing to operate normally. We construct the first…

Large language models (LLMs) are increasingly expected to function as collaborative partners, engaging in back-and-forth dialogue to solve complex, ambiguous problems. However, current LLMs often falter in real-world settings, defaulting to…

Black-box optimization refers to the optimization problem whose objective function and/or constraint sets are either unknown, inaccessible, or non-existent. In many applications, especially with the involvement of humans, the only way to…

Improving students' understanding of the nature of experimental physics is often an explicit or implicit goal of undergraduate laboratory physics courses. However, lab activities in traditional lab courses are typically characterized by…

Contribution: This study examined student effort and performance in an introductory programming course with respect to student-held implicit theories and self-efficacy. Background: Implicit theories and self-efficacy shed a light into…

Within the framework of Multi-Agent Reinforcement Learning, Social Learning is a new class of algorithms that enables agents to reshape the reward function of other agents with the goal of promoting cooperation and achieving higher global…

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

Online learning has been in the spotlight from the machine learning society for a long time. To handle massive data in Big Data era, one single learner could never efficiently finish this heavy task. Hence, in this paper, we propose a novel…