2026 Eastern European Machine Learning Summer School in Montenegro
Eastern European Machine Learning (EEML) summer school is a one-week summer school around core topics regarding machine learning and artificial intelligence.
The summer school includes both lectures and practical sessions (labs) to improve the theoretical and practical understanding of these topics. The school is organised in English and is aimed in particular at graduate students, although it is open to anyone interested in the topic.
Overview of the 2026 Eastern European Machine Learning Summer School
- Type: Summer School Training
- City: Cetinje, Montenegro
- Eligible Countries: All
- Duration: 6 Days
- Benefits: Travel costs, Accommodation, Registration Fees, Certification
- Deadline: 31st March, 2026
Financial support is awarded based on financial need rather than merit. The program covers:
- Travel Cost
- Accommodation
- Registration Fees
- Certificate of Participation
Eligibility Criteria for the 2026 Eastern European Machine Learning Summer School
- Open to All: Anyone 18 or older is welcome to apply, regardless of location.
- Diverse Backgrounds:Â Participants from various disciplines.
- Global Reach: While the school is hosted in Eastern Europe to highlight local Machine Learning talent, we encourage applications from every region of the world.
- Inclusive Environment:Â The goal is to create a vibrant, international community of researchers and practitioners.
What will you gain from Participating in the 2026 Eastern European Machine Learning Summer School
- Explore both fundamental and advanced topics in Machine Learning, including Deep Learning and Reinforcement Learning.
- Learn key terminology and core concepts in the field.
- Understand theoretical foundations, open research questions, and emerging trends.
- Gain familiarity with common neural network architectures such as CNNs, RNNs, GNNs, and Transformers.
- Learn best practices for designing experiments, setting baselines, and tuning hyperparameters.
- Develop the ability to design, train, test, and evaluate neural networks for specific tasks.
- Analyze and diagnose model behavior, including issues like overfitting.
- Network with peers and leading researchers through social events and poster sessions.