Category: Education

Posted on

New training course offering: Prompt Engineering

Course Description: Prompt Engineering

During the Fall 2024, the NCC team at UDG developed a new training offering aimed at the the use of generative AI, mos specifically at real-life LLM applications and digital transformation. The training was developed based on the communications with students and industry representatives. The initial enrollment in November was over 40 students, where most of them are expected to finish the training by 20 December.

The study of Prompt Engineering represents a cornerstone technique for effective interaction with advanced language models such as GPT-4, LLama and beyond. This course equips students with the knowledge and skills necessary to harness the transformative potential of AI technologies, emphasizing innovative, responsible, and industry-specific applications. In an era of digital transformation, where real-time decision-making and intelligent automation shape industries, the demand for high-performance computing (HPC) is critical. By exploring advanced natural language processing (NLP) models, students will not only develop effective querying techniques but also understand the computational requirements and infrastructure needed to implement these solutions at scale.

Unlocking the Power of AI: The Role of High-Performance Computing in Real-Life LLM Applications and Digital Transformation

As large language models become more sophisticated, their computational demands grow exponentially. Applications such as real-time customer interactions, predictive analytics, and decision support in fields like healthcare and education require HPC infrastructure to ensure performance and scalability. This course bridges the gap between theoretical understanding and practical implementation, highlighting how HPC enables the deployment of robust AI solutions, thus driving innovation in the digital age. Whether you’re preparing to lead AI projects in academia or industry, this course provides the essential knowledge to leverage AI technologies responsibly and effectively, positioning you at the forefront of digital transformation.

Course Content Overview (12 Modules)

  1. Introduction to Prompt Engineering – Fundamentals, significance, and applications of prompt structuring.
  2. Understanding AI Models – Overview of how language models process inputs and generate outputs.
  3. Contextual Importance – Strategies to define and provide context for optimal AI performance.
  4. Crafting Effective Prompts – Techniques for prompt structuring, tone control, and style customization.
  5. Advanced Prompting Techniques – Multi-step prompts, variable integration, and scenario-specific tasks.
  6. Experimentation and Iterative Improvement – Testing, analyzing, and refining prompts for enhanced outcomes.
  7. Industry-Specific Applications – Practical use cases in medicine, education, marketing, and law.
  8. Integrative Techniques – Combining chain-of-thought and meta-prompting for adaptability.
  9. Ethics in Prompt Engineering – Addressing bias, preventing misuse, and upholding ethical AI standards.
  10. Technical Foundations of NLP and Transformers – Key principles of NLP and the mechanics of transformers with a focus on HPC for scaling AI solutions.
  11. Real-life LLM applications, digital transformation, and the need for computing resources.
  12. Introduction ot high-performance computing and uptake to HPC considerations

Learning Outcomes

By the end of this course, students will be able to:

  • Design and structure effective prompts tailored to diverse tasks.
  • Apply advanced techniques such as chain-of-thought and meta-prompting to complex scenarios.
  • Evaluate and optimize AI model responses through iterative feedback loops.
  • Customize prompts for specific industrial needs while adhering to ethical standards.
  • Comprehend technical aspects of transformer-based NLP models.
  • LLMs and digital transformation, the need for computing resources for real-life applications
Posted on

Lecture by prof Kezunovic from Texas A&M on AI/HPC supported risk management in energy sector

As planned, the invited lecture “Risk Management of Future Large-Scale Electrification” by prof. Mladen Kezunovic took place on 25 October 2024 in Enterpreneurial nest at UDG. Threre was over 60 attendees including students, academics from Montenegrin universities and representatives from the industry. This workshop was organized in the context of HPC4S3ME project and supported by EUROCC NCC Montenegro team.

What are the risks? Methodology for risk management and mitigation? What data do we have and how do we manage all that data? How can AI/ML supported by HPC help?

Dr. Mladen Kezunovic is a University Distinguished Professor at Texas A&M with over 35 years of expertise in power engineering. Renowned globally, Dr. Kezunovic has authored over 600 papers and consulted for 50+ companies worldwide. His extensive research and industry contributions, notably in fault modeling, data analytics, and smart grids, have earned him IEEE Life Fellow status and recognition from the US National Academy of Engineering.

prof. Kezunovic from Texas A&M gave presentation on a nove approach to Risk managemement in energy sector
The workshop took place on 25 october at UDG
Over 60 people attended
How AI/ML supported by HPC can help mitigate risk in energy sector?
Posted on

Master thesis: HPC/AI for breast cancer detection

Ms. Tamara Pavlovic defended her MSc thesis on the use of HPC/AI for creating prediction models for breast cancer detection on 23.10.2024. With the support from NCC Montenegro, Ms Pavlovic did her research in the context of the HPC4S3ME project and the focus was on AI and computer vision applications in medicine. From the motivational point of view, we congratulate Tamara for finalizing and defending her thesis during the Breast Cancer Awareness Month (‘Pink October’) as people around the world adopt the pink colour and display a pink ribbon to raise awareness about breast health.

ABSTRACT – Artificial Intelligence (AI) is revolutionizing numerous sectors, including medicine, by offering innovative methods for diagnosing, treating, and researching diseases. This master’s thesis focuses on the application of AI in the diagnosis of breast cancer, using computer vision algorithms to analyze mammographic images. Through a combination of convolutional neural networks (CNNs) and deep learning, models have been developed that identify malignant changes, potentially contributing to earlier and more precise disease detection. The thesis examines in detail how AI can improve the efficiency of screening processes, reduce the time required for diagnosis, and enable a more personalized approach to treatment. In addition to technological progress, ethical issues such as patient safety and the transparency of AI systems are also considered. The results of this study confirm that the application of AI in breast cancer diagnostics can significantly enhance medical procedures. The models tested, ResNet152 and DenseNet121, demonstrated quite good performance in classifying breast cancer. Their AUC scores, which exceed the threshold of 0.9, indicate their potential for use in clinical practice. These findings not only contribute to the improvement of diagnostic processes but also open up opportunities for further research and development of AI technologies in medicine.

This research was done in th context of HPC4S3ME and with the support from EUROCC NCC Montenegro
Ms Pavlovic finalized her thesis during the Breast Cancer Awareness Month (‘Pink October’)
Posted on

Master thesis: HPC/AI in precision agriculture

Mr Mato Martinovic defended his MSc thesis on 23 octiber 2024. His research focused on detecting plant deseases for applications in vineyards. He was experimenting with HPC/AI and computer vision. He is one of the latest graduates from the AI master program created under EUROCC project and his mentoring was done with the support of EUROCC NCC Montenegro.

ABSTRACT – This research analyzes the use of computer vision in the field of viticulture. The thesis describes problems in viticulture, computer vision and its use in this field. The paper analyzed the performance of ResNet50, VGG16 and MobileNet models in the classification of diseases and grapevine species. The models achieved accuracy of 98.67%, 97.28%, and 98.72% on the original test data set, while on the extended one, they achieved 87.47%, 72.07%, and 86.64%, respectively, when classifying diseases. In species classification, the models achieved accuracies of 70%, 78% and 88% on the original test data set, and 66%, 51% and 72% on the extended one, respectively. The VGG-16 model had the largest difference in accuracy over extended data, while ResNet had the smallest decrease in accuracy in both cases, which implies that ResNet generalizes the data better. The paper presents the process of creating a platform that allows users to post an image and receive a prediction value through a mobile application.

HPC/AI and computer vision for applications in smart viticulture
Posted on

Master thesis: Deep learning in energy sector

Ms. Zoja Scekic, a young researcher on HPC4S3ME project, defended her MSc thesis “Deep learning and applications in energy sector” today. This is one of the main project outputs in capacity building aimed at HPC/AI skills for applications in priority domains of Montenegrin S3.

ABSTRACT – This master’s thesis explores the application of advanced deep learning models for predicting day-ahead electricity prices, focusing on the accuracy and efficiency of these models compared to traditional forecasting methods. With the increasing integration of renewable energy sources and the growing complexity of electricity markets, accurate price forecasting has become crucial for market participants, grid operators, and policymakers. The research is structured around four case studies, each employing different deep learning techniques, such as Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and hybrid models like CNN-LSTM. Despite the promising results, the research recognizes limitations related to data quality, model complexity, and computational resource requirements. The study emphasizes the need for further research into optimizing model efficiency, integrating more diverse data sources, and expanding the applicability of these models to different energy markets.

Ms Zoja Scekic defended her MSc thesis on Deep leaning applications in energy sector
This MSc thesis was done in the context of HPC4S3ME with support from EUROCC NCC Montenegro
Posted on

Upcoming Lecture: “Risk Management of Future Large-Scale Electrification”

The global shift towards large-scale electrification brings significant opportunities, yet also introduces complex risks that require our immediate attention. Join us for an insightful lecture by Prof. Mladen Kezunovic, a leader in power engineering and data analytics, as he delves into the challenges and risks posed by the evolution of the electric grid.

Prof. Kezunovic will outline the motivation behind large-scale electrification, addressing the unique vulnerabilities emerging from critical infrastructure interdependencies. This talk will highlight risks such as environmental impacts, aging infrastructure, the rise of distributed energy resources, digitalization challenges, and behavioral factors. Prof. Kezunovic will discuss innovative machine learning and artificial intelligence solutions for predicting and mitigating these risks, offering a glimpse into the future of resilient grid design.

Invited lecture from distinguished professor from Texas A&M

Attendees will gain insight into an essential case study on the State-of-Risk-Prediction for grid outages, shedding light on the shift toward a risk-informed control and protection paradigm. The discussion will touch on a holistic approach encompassing IT management, big data, interoperability, and high-performance computing, emphasizing the necessity of these tools for advancing data analytics and AI-powered solutions in electrification. This lecture is organized with the support of EUROCC NCC Montenegro and HPC4S3ME.

About the Speaker: Dr. Mladen Kezunovic is a University Distinguished Professor at Texas A&M with over 35 years of expertise in power engineering. Renowned globally, Dr. Kezunovic has authored over 600 papers and consulted for 50+ companies worldwide. His extensive research and industry contributions, notably in fault modeling, data analytics, and smart grids, have earned him IEEE Life Fellow status and recognition from the US National Academy of Engineering. Don’t miss this chance to learn from one of the foremost experts in the field!

Posted on

Cross-NCCs training event: “Machine Learning for Multiple Domains”

NCC Türkiye, NCC Serbia, NCC Montenegro, and NCC North Macedonia are pleased to announce a joint online training event titled “Machine Learning for Multiple Domains: From Concepts to Implementation,” scheduled for October 14-15, 2025, starting at 10:00 AM.

Participants can expect engaging program at both beginner and intermediate levels and will feature hands-on sessions along with key presentations spread across two days: Brief introductions on HPC/AI activities by 4 NCCs; Supercomputing access demo (TRUBA HPC infrastructure), presentations from NCC Macedonia (Design, Develop, Deploy, and Iterate on Production-Grade ML Applications) and NCC Turkey (Protein Language Models and Using Them for Downstream Prediction Tasks) on Day 1, and presentations from NCC Serbia (Modeling of Large-Scale Social Data) and NCC Montenegro (Analyzing Social Media Trends) on Day 2.

We look forward to your participation in this valuable opportunity to enhance your skills in HPC and machine learning!

More information on the training program, timetable and registration details you can find here: https://indico.truba.gov.tr/e/ML4MultipleDomains

Privacy Policy Proudly powered by WordPress