Related papers: E-Gotsky: Sequencing Content using the Zone of Pro…
During their first years of life, infants learn the language(s) of their environment at an amazing speed despite large cross cultural variations in amount and complexity of the available language input. Understanding this simple fact still…
We continuously interact with computerized systems to achieve goals and perform tasks in our personal and professional lives. Therefore, the ability to program such systems is a skill needed by everyone. Consequently, computational thinking…
Distributed synchronized GPU training is commonly used for deep learning. The resource constraint of using a fixed number of GPUs makes large-scale training jobs suffer from long queuing time for resource allocation, and lowers the cluster…
Neural Machine Translation (NMT) models have become successful, but their performance remains poor when translating on new domains with a limited number of data. In this paper, we present a novel approach Epi-Curriculum to address…
Logit-based knowledge distillation (KD) for classification is cost-efficient compared to feature-based KD but often subject to inferior performance. Recently, it was shown that the performance of logit-based KD can be improved by…
Text classification is a fundamental task for natural language processing, and adapting text classification models across domains has broad applications. Self-training generates pseudo-examples from the model's predictions and iteratively…
The absence of an algorithm that effectively monitors deep learning models used in side-channel attacks increases the difficulty of evaluation. If the attack is unsuccessful, the question is if we are dealing with a resistant implementation…
Human-annotated datasets with explicit difficulty ratings are essential in intelligent educational systems. Although embedding vector spaces are widely used to represent semantic closeness and are promising for analyzing text difficulty,…
Despite the precision and adaptiveness of generative AI (GAI)-powered feedback provided to students, existing practice and literature might ignore how usage patterns impact student learning. This study examines the heterogeneous effects of…
This work presents an architecture that generates curiosity-driven goal-directed exploration behaviours for an image sensor of a microfarming robot. A combination of deep neural networks for offline unsupervised learning of low-dimensional…
Embedding-based retrieval serves as a dominant approach to candidate item matching for industrial recommender systems. With the success of generative AI, generative retrieval has recently emerged as a new retrieval paradigm for…
Test-time adaptation offers a promising avenue for improving reasoning performance in large language models without additional supervision, but existing approaches often apply a uniform optimization objective across all inputs, leading to…
Given the variability in student learning it is becoming increasingly important to tailor courses as well as course sequences to student needs. This paper presents a systematic methodology for offering personalized course sequence…
Knowledge distillation is used, in generative language modeling, to train a smaller student model using the help of a larger teacher model, resulting in improved capabilities for the student model. In this paper, we formulate a more general…
Knowledge distillation is an attractive approach for learning compact deep neural networks, which learns a lightweight student model by distilling knowledge from a complex teacher model. Attention-based knowledge distillation is a specific…
Scrum is one of the most used frameworks for agile software development because of its potential improvements in productivity, quality, and client satisfaction. Academia has also focussed on teaching Scrum practices to prepare students to…
Robots have the potential to enhance teaching of advanced computer science topics, making abstract concepts more tangible and interactive. In this paper, we present Timmy-a GoPiGo robot augmented with projections to demonstrate shortest…
Learning dynamics from dissipative chaotic systems is notoriously difficult due to their inherent instability, as formalized by their positive Lyapunov exponents, which exponentially amplify errors in the learned dynamics. However, many of…
Continued pre-training of small language models offers a promising path for domain adaptation with limited computational resources. I've investigated this approach within educational domains, evaluating it as a resource-efficient…
A teaching experiment was carried out in a university-level thermodynamics course using adaptive and interactive e-learning material, created in the new Moodle question type Stateful extending the original e-learning platform STACK. The…