Ourania Spantidi

Dr. Ourania Spantidi

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 February 2025 in IEEE Transactions on Learning Technologies
Verified
Journal Article
Closed access
KTKaitlyn Tracy
Kaitlyn Tracy
OSOurania Spantidi
Ourania Spantidi
Virtual reality (VR) has emerged as a transformative educational tool, enabling immersive learning environments that promote student engagement and understanding of complex concepts. However, despite the growing adoption of VR in education, there remains a significant gap in research exploring how generative AI such as GPT can further enhance these experiences by reducing cognitive load and improving learning outcomes. This study examines the impact of an AI-driven instructor assistant in VR classrooms on student engagement, cognitive load, knowledge retention, and performance. A total of 52 participants were divided into two groups experiencing a VR lesson on the bubble sort algorithm, one with only a pre-scripted virtual instructor (control group), and the other with the addition of an AI instructor assistant (experimental group). Statistical analysis of post-lesson quizzes and cognitive load assessments was conducted using independent t-tests and ANOVA, with the cognitive load being measured through a post-experiment questionnaire. The study results indicate that the experimental group reported significantly higher engagement compared to the control group. While the AI assistant did not significantly improve post-lesson assessment scores, it enhanced conceptual knowledge transfer. The experimental group also demonstrated lower intrinsic cognitive load, suggesting the assistant reduced the perceived complexity of the material. Higher germane and general cognitive loads indicated that students were more invested in meaningful learning without feeling overwhelmed.

6 June 2022 in IEEE Transactions on Emerging Topics in Computing
Verified
Journal Article
Closed access
OSOurania Spantidi
Ourania Spantidi
GZGeorgios Zervakis
Georgios Zervakis
SASami Alsalamin
Sami Alsalamin
IRIsai Roman-Ballesteros
Isai Roman-Ballesteros
JHJörg Henkel
Jörg Henkel
IAIraklis Anagnostopoulos
Iraklis Anagnostopoulos
Modern applications rely more and more on the simultaneous execution of multiple DNNs, and Heterogeneous DNN Accelerators (HDAs) prevail as a solution to this trend. In this work, we propose, implement, and evaluate low precision Neural Processing Units (NPUs) which serve as building blocks to construct HDAs, to address the efficient deployment of multi-DNN workloads. Moreover, we design and evaluate HDA designs that increase the overall throughput, while reducing the energy consumption during NN inference. At the design time, we implement HDAs inspired by the big.LITTLE computing paradigm, consisting of 8-bit NPUs together with lower precision bit-width NPUs. Additionally, an NN-to-NPU scheduling methodology is implemented to decide at run-time how to map the executed NN to the suitable NPU based on an accuracy drop threshold value. Our hardware/software co-design reduces the energy and response time of NNs by 29% and 10% respectively when compared to state-of-the-art homogeneous architectures. This comes with a negligible accuracy drop of merely 0.5%. Similar to the traditional CPU big.LITTLE, our asymmetric NPU design can open new doors for designing novel DNN accelerator architectures, due to their profound role in increasing the efficiency of DNNs with minimal losses in accuracy.

1 November 2021
Verified
Conference Paper
Open access
OSOurania Spantidi
Ourania Spantidi
GZGeorgios Zervakis
Georgios Zervakis
IAIraklis Anagnostopoulos
Iraklis Anagnostopoulos
HAHussam Amrouch
Hussam Amrouch
JHJorg Henkel
Jorg Henkel
Recent Deep Neural Networks (DNNs) manage to deliver superhuman accuracy levels on many AI tasks. DNN accelerators are becoming integral components of modern systems-on-chips. DNNs perform millions of arithmetic operations per inference and DNN accelerators integrate thousands of multiply-accumulate units leading to increased energy requirements. To lower the energy consumption of DNN accelerators, approximate computing principles are employed. However, complex DNNs can be increasingly sensitive to approximation. In this work, we present a dynamically configurable approximate multiplier that supports three operation modes, i.e., exact, positive error, and negative error. In addition, we propose a filter-oriented approximation method to map the weights to the appropriate modes of the approximate multiplier. Our mapping algorithm balances the positive with the negative errors due to the approximate multiplications, aiming at maximizing the energy reduction while minimizing the overall convolution error. We evaluate our approach on multiple DNNs and datasets against state-of-the-art approaches, where our method achieves 18.33% energy gains on average across 7 NNs on 4 different datasets for a maximum accuracy drop of only 1%.

6 January 2022 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
GZGeorgios Zervakis
Georgios Zervakis
IAIraklis Anagnostopoulos
Iraklis Anagnostopoulos
SSSami Salamin
Sami Salamin
OSOurania Spantidi
Ourania Spantidi
IRIsai Roman-Ballesteros
Isai Roman-Ballesteros
HAHussam Amrouch
Hussam Amrouch
Recent breakthroughs in Neural Networks (NNs) have made DNN accelerators ubiquitous and led to an ever-increasing quest on adopting them from Cloud to edge computing. However, state-of-the-art DNN accelerators pack immense computational power in a relatively confined area, inducing significant on-chip power densities that lead to intolerable thermal bottlenecks. Existing state of the art focuses on using approximate multipliers only to trade-off efficiency with inference accuracy. In this work, we present a thermal-aware approximate DNN accelerator design in which we additionally trade-off approximation with temperature effects towards designing DNN accelerators that satisfy tight temperature constraints. Using commercial multi-physics tool flows for heat simulations, we demonstrate how our thermal-aware approximate design reduces the temperature from 139 $^{\circ }$ C, in an accurate circuit, down to 79 $^{\circ }$ C. This enables DNN accelerators to fulfill tight thermal constraints, while still maximizing the performance and reducing the energy by around 75% with a negligible accuracy loss of merely 0.44% on average for a wide range of NN models. Furthermore, using physics-based transistor aging models, we demonstrate how reductions in voltage and temperature obtained by our approximate design considerably improve the circuit’s reliability. Our approximate design exhibits around 40% less aging-induced degradation compared to the baseline design.

9 August 2022 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
OSOurania Spantidi
Ourania Spantidi
GZGeorgios Zervakis
Georgios Zervakis
IAIraklis Anagnostopoulos
Iraklis Anagnostopoulos
JHJorg Henkel
Jorg Henkel
Deep neural networks (DNNs) are being heavily utilized in modern applications, putting energy-constraint devices to the test. To bypass high energy consumption issues, approximate computing has been employed in DNN accelerators to balance out the accuracy-energy reduction trade-off. However, the approximation-induced accuracy loss can be very high and drastically degrade the performance of the DNN. Therefore, there is a need for a fine-grain mechanism that would assign specific DNN operations to approximation to maintain acceptable DNN accuracy, while achieving low energy consumption. We present an automated framework for weight-to-approximation mapping through formal property exploration for approximate DNN accelerators. At the MAC unit level, our experimental evaluation surpassed already energy-efficient mappings by more than $\times 2$ in terms of energy gains, while supporting a fine-grain control over the introduced approximation.

23 July 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
LKLazaros Rafail Kouzelis
Lazaros Rafail Kouzelis
OSOurania Spantidi
Ourania Spantidi
Extended reality offers unique ways to create mediated spaces that enhance and help popularize experiences across several domains, including entertainment, creativity, and culture. There are still issues that hinder the widespread adoption of the medium, such as the over-reliance on scripted sequences, generalized approaches, and curated asset production. Artificial intelligence can be used to, in part, alleviate these issues, but this comes with its own set of challenges, such as factual inaccuracy or hallucinations. We delve into prompt engineering methods for the GPT API, enhancing context understanding to enable more realistic performances in historical event recreations. Specifically, we experiment with the Great Fire of Smyrna in 1922 as our historical context, situating the AI agent in the middle of chaos as a resident that has been affected by the event. Our experiments demonstrate that refined prompt engineering techniques significantly reduce factual inaccuracies and enhance the emotional resonance of AI-generated dialogues, which can lead to more immersive and engaging XR experiences. Our experiments indicate that AI can effectively support historical recreations by providing dynamic and contextually appropriate interactions.