Vanja Doskoc

Research Interests

• Inductive Inference or Language Learning in the Limit
• Deep Learning and Neural Networks
• Applications of Evolutionary Algorithms
• Explainable AI

On my research page you can find an introduction and desription of my work regarding inductive inference. Furthermore, you can find a video (presented in the 17th IREBS Real Estate Symposium) where we present our work on an automated real estate valuation process compliant with German law.

Teaching Activities

As Advisor

Bachelor Theses

• Explaining the Predictions of Any Time Series Classifier, Felix Mujkanovic (Summer '19)
• Valuation of Real Estate Properties using Data-Driven Similarity Search, Ben Bals (Summer '21)
• Approximate k-Nearest-Neighbor Queries on Geographic Data in the Context of Real Estate Valuation, Niko Hastrich (Summer '21)
• Finding Deep Neural Network Architectures for Tabular Real Estate Data Using Genetic Algorithms, Maximilian Kleissl (Summer '21)
• Preparation of Real Estate Data for Deep Learning, Lukas Weyand (Summer '21)
• Isomorphisms and Embeddings between Limit Learning Settings, Paula Marten (Summer '22)
• Behaviorally Correct Learning from Informants, Niklas Mohrin (Summer '22)
• The Utility of Clustering for Real Estate Valuation, Kathrin Thenhausen (Summer '22)

Bachelor Projects

• Improving Real-Estate Valuation (Winter '20 and Summer '21)
• Next Generation Real-Estate Valuation (Winter '21 and Summer '22)

Master Theses

• Identifying Vehicle Parking Lots from Aerial Images using Deep Learning Methods, Bashini Mahaarachchi (Winter '21)

As Teaching Assistant

• Project seminar on "Computability- and Learningtheory" (German, Winter '19)
• Second basic course of Mathematics (German, Summer '20, Summer '21, Summer '22) as well as a specific specialization thereof (German, Summer '21, Summer '22)
• Project seminar on "Competitive Programming with Deep Learning" (Winter '20)
• Project seminar on "Deep Learning for Combinatorial Optimization" (Summer '21)
• Seminar on "Theory of Artificial Intelligence" (German, Winter '21)
• Project seminar on "Competitive Programming with Deep Learning 2" (Winter '21, Winter '22)
• Project seminar on "Deep Learning for Optical Character Recognition" (Winter '22)

Publications

2023

•  

  Krämer, Bastian; Stang, Moritz; Doskoč, Vanja; Schäfers, Wolfgang; Friedrich, TobiasAutomated valuation models: improving model performance by choosing the optimal spatial training levelJournal of Property Research 2023: 365–390

  [ ][ ][ URL ][ DOI ][ Download ]

•  

  Krämer, Bastian; Stang, Moritz; Doskoč, Vanja; Schäfers, Wolfgang; Friedrich, TobiasAutomated Valuation Models: Improving Model Performance by Choosing the Optimal Spatial Training LevelAmerican Real Estate Society (ARES) 2023: 1–26

  [ ][ ][ URL ][ DOI ][ Download ]

2022

•  

  Hildebrandt, Philipp; Schulze, Maximilian; Cohen, Sarel; Doskoč, Vanja; Saabni, Raid; Friedrich, TobiasOptical Character Recognition Guided Image Super ResolutionSymposium on Document Engineering (DocEng) 2022: 1–4

  [ ][ ][ URL ][ DOI ][ Download ]

•  

  Doskoč, Vanja; Kötzing, TimoMaps of Restrictions for Behaviourally Correct LearningComputability in Europe (CiE) 2022: 103–114

  [ ][ ][ URL ][ DOI ][ Download ]

•  

  Angrick, Sebastian; Bals, Ben; Hastrich, Niko; Kleissl, Maximilian; Schmidt, Jonas; Doskoč, Vanja; Katzmann, Maximilian; Molitor, Louise; Friedrich, TobiasTowards Explainable Real Estate Valuation via Evolutionary AlgorithmsGenetic and Evolutionary Computation Conference (GECCO) 2022: 1130–1138

  [ ][ ][ URL ][ DOI ][ Download ]

2021

•  

  Berger, Julian; Bleidt, Tibor; Büßemeyer, Martin; Ding, Marcus; Feldmann, Moritz; Feuerpfeil, Moritz; Jacoby, Janusch; Schröter, Valentin; Sievers, Bjarne; Spranger, Moritz; Stadlinger, Simon; Wullenweber, Paul; Cohen, Sarel; Doskoč, Vanja; Friedrich, TobiasFine-Grained Localization, Classification and Segmentation of Lungs with Various DiseasesCVPR Workshop on Fine-Grained Visual Categorization (FGVC@CVPR) 2021

  [ ][ ][ URL ][ Download ]

•  

  Doskoč, Vanja; Kötzing, TimoNormal Forms for Semantically Witness-Based Learners in Inductive InferenceComputability in Europe (CiE) 2021: 158–168

  [ ][ ][ URL ][ DOI ][ Download ]

•  

  Doskoč, Vanja; Kötzing, TimoMapping Monotonic Restrictions in Inductive InferenceComputability in Europe (CiE) 2021: 146–157

  [ ][ ][ URL ][ DOI ][ Download ]

•  

  Berger, Julian; Böther, Maximilian; Doskoč, Vanja; Gadea Harder, Jonathan; Klodt, Nicolas; Kötzing, Timo; Lötzsch, Winfried; Peters, Jannik; Schiller, Leon; Seifert, Lars; Wells, Armin; Wietheger, SimonLearning Languages with Decidable HypothesesComputability in Europe (CiE) 2021: 25–37

  [ ][ ][ URL ][ DOI ][ Download ]

•  

  Kißig, Otto; Taraz, Martin; Cohen, Sarel; Doskoč, Vanja; Friedrich, TobiasDrug Repurposing for Multiple COVID Strains using Collaborative FilteringICLR Workshop on Machine Learning for Preventing and Combating Pandemics (MLPCP@ICLR) 2021

  [ ][ ][ Download ]

•  

  Quinzan, Francesco; Doskoč, Vanja; Göbel, Andreas; Friedrich, TobiasAdaptive Sampling for Fast Constrained Maximization of Submodular FunctionsArtificial Intelligence and Statistics (AISTATS) 2021: 964–972

  [ ][ ][ URL ][ Download ]

2020

•  

  Doskoč, Vanja; Friedrich, Tobias; Göbel, Andreas; Neumann, Aneta; Neumann, Frank; Quinzan, FrancescoNon-Monotone Submodular Maximization with Multiple Knapsacks in Static and Dynamic SettingsEuropean Conference on Artificial Intelligence (ECAI) 2020: 435–442

  [ ][ ][ DOI ][ Download ]

•  

  Doskoč, Vanja; Kötzing, TimoCautious Limit LearningAlgorithmic Learning Theory (ALT) 2020: 251–276

  [ ][ ][ URL ][ Download ]

2018

•  

  Doskoč, VanjaConfident Iterative Learning in Computational Learning TheoryCurrent Trends in Theory and Practice of Computer Science (SOFSEM) 2018: 30–42

  [ ][ ][ Download ]