Related papers: CryptoEL: A Novel Experiential Learning Tool for E…
Existing reinforcement learning environment libraries use monolithic environment classes, provide shallow methods for altering agent observation and action spaces, and/or are tied to a specific simulation environment. The Core Reinforcement…
Electromyography (EMG)-based gesture recognition is a promising approach for designing intuitive human-computer interfaces. However, while these systems typically perform well in controlled laboratory settings, their usability in real-world…
Continual learning (CL) studies the problem of learning a sequence of tasks, one at a time, such that the learning of each new task does not lead to the deterioration in performance on the previously seen ones while exploiting previously…
Because of todays technological developments and the influence of digital systems into every aspect of our lives, importance of cyber security improves more and more day-by-day. Projects, educational processes and seminars realized for this…
Continual Learning is an unresolved challenge, whose relevance increases when considering modern applications. Unlike the human brain, trained deep neural networks suffer from a phenomenon called catastrophic forgetting, wherein they…
Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and…
Secondary school students increasingly encounter AI systems whose outputs depend on data quality, evaluation choices and modeling assumptions. To provide accessible entry points to these interconnected concepts, we developed…
Communication bottlenecks and the presence of stragglers pose significant challenges in distributed learning (DL). To deal with these challenges, recent advances leverage unbiased compression functions and gradient coding. However, the…
Continual Learning (CL) investigates how to train Deep Networks on a stream of tasks without incurring forgetting. CL settings proposed in literature assume that every incoming example is paired with ground-truth annotations. However, this…
Building on successful work on studying and transforming our senior-level Advanced Lab course, we have transformed our junior-level Electronics course to engage students in a variety of authentic scientific practices, including…
In-context learning (ICL) has emerged as a powerful capability of transformer-based language models, enabling them to perform tasks by conditioning on a small number of examples presented at inference time, without any parameter updates.…
Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…
Cryo-Electron Tomography (cryo-ET) is a new 3D imaging technique with unprecedented potential for resolving submicron structural detail. Existing volume visualization methods, however, cannot cope with its very low signal-to-noise ratio. In…
Class-Incremental Learning (CIL) enables models to learn new classes continually while preserving past knowledge. Recently, vision-language models like CLIP offer transferable features via multi-modal pre-training, making them well-suited…
The purpose of this feasibility study was to examine the potential impact of reading digital interactive e-books on essential skills that support reading comprehension with third-fifth grade students. Students read two e-Books that taught…
The computing education community endeavors to consistently move forward, improving the educational experience of our students. As new innovations in computing education practice are learned and shared, however, these papers may not exhibit…
What do different contrastive learning (CL) losses actually optimize for? Although multiple CL methods have demonstrated remarkable representation learning capabilities, the differences in their inner workings remain largely opaque. In this…
This study introduces the AI-Educational Development Loop (AI-EDL), a theory-driven framework that integrates classical learning theories with human-in-the-loop artificial intelligence (AI) to support reflective, iterative learning.…
This paper tackles the problem of designing efficient binary-level verification for a subset of information flow properties encompassing constant-time and secret-erasure. These properties are crucial for cryptographic implementations, but…
We introduce CoT-ICL Lab, a framework and methodology to generate synthetic tokenized datasets and systematically study chain-of-thought (CoT) in-context learning (ICL) in language models. CoT-ICL Lab allows fine grained control over the…