Blood pressure (BP) is a crucial indicator of cardiovascular health. Hypertension is a common life-threatening condition and a key factor of cardiovascular diseases (CVDs). Identifying abnormal BP fluctuations can allow for early detection and management o ...
Language has shaped human evolution and led to the desire to endow machines with language abilities. Recent advancements in natural language processing enable us to achieve this breakthrough in human-machine interaction. However, introducing conversational ...
Over the past few decades, the debates have shifted from whether to how Computer Science (CS) should be introduced into formal education. Given the diverse ways to introduce CS into formal education, and the struggles many countries have faced, considerabl ...
Finding optimal bidding strategies for generation units in electricity markets would result in higher profit. However, it is a challenging problem due to the system uncertainty which is due to the lack of knowledge of the strategies of other generation uni ...
The recent rise in both popularity and performance of large language models has garnered considerable interest regarding their applicability to education. Technologies like ChatGPT, which can engage in human-like dialog, have already disrupted educational ...
Addressing the complex challenges of sustainability demands for good teamwork abilities for future technicians and engineers. In our three institutions we adopted project-based learning to facilitate the development of these skills – but is this enough? Si ...
Large language models (LLMs) have been leveraged for several years now, obtaining state-of-the-art performance in recognizing entities from modern documents. For the last few months, the conversational agent ChatGPT has "prompted" a lot of interest in the ...
Inclusive teaching is the intentional practice of recognising biases, working to mitigate their impact, and ensuring that students have equitable learning opportunities. In addition to improving students' sense of belonging and self efficacy, inclusive tea ...
In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...
Model-free Reinforcement Learning (RL) generally suffers from poor sample complexity, mostly due to the need to exhaustively explore the state-action space to find well-performing policies. On the other hand, we postulate that expert knowledge of the syste ...
