Dipl.-Inform. Ruben Nuredini

Intelligent Systems

This course provides a comprehensive exploration of the field of Artificial Intelligence, encompassing various aspects of AI and its applications. Throughout the course, students are exposed to a diverse range of lecture units that provide a solid foundation and practical insights into intelligent systems. Students learn about various learning paradigms, such as supervised, unsupervised, and reinforcement learning, and discover how these methods can be applied in real-world scenarios. Additionally, students delve into techniques for data collection, processing, and analysis. They gain insights into the challenges associated with acquiring high-quality and diverse data, and explore strategies for effective data management and preprocessing. Finally, the course addresses the challenges and ethical implications associated with the AI revolution. Students critically analyze the societal impacts, biases, privacy concerns, and ethical dilemmas arising from the widespread adoption of AI technologies.

Deep Learning

This course provides a technical appoach to the field of Artificial Intelligence. Students explore advanced neural networks and their applications in Computer Vision, Sequential Data Processing, Natural Language Understanding, Generative Models, and Reinforcement Learning. Through practical programming assignments, students gain hands-on experience with cutting-edge Deep Learning frameworks and datasets. They learn to analyze data, implement sophisticated predictive models, evaluate performance, identify areas for improvement, and fine-tune models for optimal results. The course emphasizes leveraging cutting-edge techniques and translating them into practical applications. By the course's conclusion, students are equipped with the knowledge and skills to effectively apply Deep Learning techniques to real-world problems, contributing to the ongoing advancements in the field of Artificial Intelligence.

Machine Learning

This course provides a comprehensive study of the field of "Machine Learning" equipping students with the knowledge and skills to effectively leverage related techniques. Topics covered include regression, classification, document retrieval , clustering, recommender systems and dimensionality reduction. Students learn about feature selection, dataset preprocessing, cross-validation techniques, regularization techniques, overfitting prevention, proper evaluation and assessment of machine learning models as well as scaling machine learning to large datasets. The course addresses: Decision Trees, Boosting, Principal Component Analysis , Stochastic Gradient Descent, Nearest Neighbor Search, K-Means, Mixture Models, Latent Dirichlet Allocation, Principal Component Analysis etc. By course completion, students possess a comprehensive understanding of machine learning principles and algorithms,

Data Science Lab

Through practical exercises, students gain hands-on experience implementing and evaluating machine learning models enabling them to apply machine learning techniques to real-world problems.

Available topics for Bachelor/Master Thesis:

• Data Collection Framework for Adolescent Scoliosis Patients
• Adaptive User Interfaces with Reinforcement Learning: from Data Collection to Fine-Tuning
• Large Language Models in Academic Setting
• Document Embedding Techniques: Automated Collection, Clustering and Retrieval of Scientific Publications
• Systematic Overview of Reinforcement Learning Programming Frameworks
• Benchmarking Collaboration/Communication Tools in University Context

List of supervised theses

• Master Theses
  • "Academic Coursework Assessment and Feedback Generation with LLMs", 2024
  • "Machine Learning for Engine Performance Data Analysis: Evaluation of Methods to Support Decision Making and Interpretation", 2024
  • "Adaptive VR Movement Therapy for Patients with Functional Disabilities in the Upper Extremities", 2024
  • “Cloud-Based Technologies for High-Performance Realtime Ingestion and Processing of Racing Data", 2023
  • “Investigation of Machine Learning Approaches to Improve the Calibration of Laser Positions", 2023
  • “Pose Estimation 3D Re-rendering Real-Time Style Transfer Pipeline", 2023
  • “Object Classification Model Based on Ultrasonic Data: Techniques for Training Set Optimization", 2022
  • "Analysis of an Advanced Deployment with Kubernetes (using Weaveworks Flagger)", 2020
  • "Investigation of AI-Driven Software Optimization to Reduce the Consumption of Microcontroller Resources", 2020
  • "Efficient Storage, Labeling and Querying of Automotive Data in a Big Data Cluster", 2019
  • "Supervised Learning for Evaluating the Quality of Individual Data in Open Knowledge Databases", 2017

• Bachelor Theses
  • "Systematic Evaluation of Document Embedding Techniques", 2024
  • "Kooperative Spielszenarien mit Multi-Agent Reinforcement Learning im Kontext von Unity ML-Agents ", 2021
  • "Maschinelles Lernern in Unity ML-Agents im Kontext des autonomes Fahren", 2021
  • "Anwendung von Reinforcement Learning mit Unity ML Agents", 2021
  • "Automatische Generierung von synthetischen Trainingsdatensätzen für die Objekterkennung innerhalb Bildmaterials durch ein Neuronales Netzwerk", 2020
  • "Beyond Convolutional Neural Networks – Computer Vision with Capsule Networks", 2019
  • "NEAT: Neuroevolution of Augmented Topologies", 2019
  • "Functional Programming in Education", 2017
  • "Visualisierung Studentischen Verhaltens in einer E-Learning-Platform", 2016

Doctor in Computer Sciences

• Ph.D. Thesis: "Biologically-Inspired Autonomous Agent Navigation using Reinforcement Learning Algorithm", South East European University (SEEU), 2012 - 2017

International Activities

• "Workshop: Applied Machine Learning", ETSINF, UPV Universitat Politècnica de València, 2022
• "Workshop: Applied Reinforcement Learning", South-East European University, Tetovo, Republic of Macedonia, 2024
• "Workshop: Reinforcement Learning - Shaping the Reward Function", ETSINF, UPV Universitat Politècnica de València, 2024
• EU Project: Social Implications of Artificial Intelligence (AI), Erasmus+ KA131 – Blended Intensive Programme (BIP) (2024)

Research Work

• "Reinforcement Learning-Based Framework for the Intelligent Adaptation of User Interfaces", D.G. Figueiredo, M. Fernandez-Diego, R. Nuredini, S. Abrahão, E. Insfran, EICS Companion '24: Companion Proceedings of the 16th ACM SIGCHI Symposium on Engineering Interactive Computing Systems, June 2024 (https://doi.org/10.1145/3660515.3661329)
• "Integrating Human Feedback to Guide the Intelligent Adaptation of User Interfaces", D.G. Figueiredo, M. Fernandez-Diego, S. Abrahão, E. Insfran, R. Nuredini, Proceedings of the XXVIII Conference on Software Engineering and Databases, June 2024 (https://hdl.handle.net/11705/JISBD/2024/85)
  
• "Autonomous Driving with Reinforcement Learning", Master Projekt, Mechatronics & Robotics, Faculty of Mechanics and Electronics, Heilbronn University of Applied Science, 2020
• "Air-Hockey mit Reinforcement Learning", Master Projekt, Mechatronics & Robotics, Faculty of Mechanics and Electronics, Heilbronn University of Applied Science, 2020
• "Reactive Vision-Based Navigation Controller for Autonomous Mobile Agents", International Conference of Artificial Intelligence, Limerick City, Ireland 2016 
• "Bio-Inspired Obstacle Avoidance: from Animals to Intelligent Agents", International Conference of Artificial Intelligence, Limerick City, Ireland 2016 
• "A Review of Animal Behavior-Inspired Methods for Intelligent Systems", SAI Intelligent Systems Conference, London, UK 2016
• "Comparative Performance Analysis of M/M/C and Multiple Single-Server Queuing Systems in SimEvents",  Informacione Tehnologije - IT, Zabljak, Montenegro 2012
• "Analytical and simulation performance analysis for parallel M/M/1 queuing system", ICEST, Nis, Serbia 2011
• "Comparative Study of Analytical and Simulation Performance Results of Pay-Toll Areas", Automation in Transportation, Pula, Croatia and Milano, Italy 2011