Schedule

Detailed information about the activities

Statistics for data science (Dan Nicolae)

• Foundations of data analysis
• Statistical inference with resampling methods
• Probability and simulations

Machine learning (Dan Nicolae)

• Linear models and inference
• Model complexity
• Prediction and classification
• Neural networks

Large Language Models (LLMs) – reasoning capabilities and model calibration (Cornelia Caragea)

• Prompting strategies in LLMs – Zero-Shot vs. In-Context Learning
• LLMs reasoning capabilities
• LLMs calibration – do they know what they do not know?

Knowledge Graphs for LLMs, Agents, and Auditable AI (Dumitru Roman)

• From retrieval with LLMs to graphs
• Knowledge graph construction and querying
• Graph algorithms
• Graph-based agent memory and provenance

Agentic AI (Nikolay Nikolov)

• Agent loops and state
• Tool selection and contracts
• Planning, verification and recovery
• Safety, tracing and evaluation

Conversational AI (Ioan Toma)

• Conversational AI setup and designing a chatbot interface
• Semantic Knowledge Graphs and their role in Conversational AI
• Building a chatbot using Onlim Conversational AI framework

Time series: Forecasting, XAI, and databases (Jože Rožanec)

• Using network models to represent and forecast time series
• Introduction to explainability methods
• Introduction to time series databases

Causal AI (Jože Rožanec)

• Introductory concepts
• Causal discovery: time series, LLMs, images
• Applications

Edge Federated Learning (Radu Prodan)

• Distributed and decentralized learning
• Parallel computing for AI workloads
• Federated Learning: concepts, architectures, and challenges
• Communication and privacy in federated systems
• Federated learning on edge devices
• Implementation in Flower