• E-mailAna.Ozaki@uib.no
  • Phone+47 55 58 41 76
  • Visitor Address
    HIB - Thormøhlens gate 55
  • Postal Address
    Postboks 7803
    5020 Bergen

Ana Ozaki is an associate professor at the University of Bergen, Norway. Her research area is Artificial Intelligence (AI). She is an AI researcher in the field of knowledge representation and reasoning and in learning theory.

Ozaki is interested in the formalisation of the learning phenomenon so that questions involving learnability, complexity, and reducibility can be systematically investigated and understood. Her research focuses on learning logical theories formulated in description logic and related formalisms for knowledge representation.

She is a member of the editorial boards of the Journal of Machine Learning Research and the Journal of Web Semantics. She has recently worked as Program Committee Chair for the 27th International Symposium on Temporal Representation and Reasoning.

Ozaki is fascinated by learning and reasoning processes and how they interact.

There is a mode of learning which is actually how we learn very often but that is not the mode of learning we refer to when we talk about machine learning. We learn very often by posing queries (questions). Our intuition is that by obtaining answers to our questions from a teacher we can learn faster and better (more accurately) than by randomly selecting learning material. In learning theory, one can show that learners can efficiently exactly identify an unknown target concept formulated e.g. as a deterministic finite automaton, a decision tree, or a set of Horn rules if they can pose queries to a teacher.

Ozaki is currently working with her team on strategies to learn Horn rules from neural networks by posing them queries. She believes that exciting and recent advances in machine learning need to be complemented with theoretical development so that systems can provide formal guarantees of classification results and become trustable.


Open position: PhD Research Fellows in Informatics - Knowledge Representation and Machine Learning


AAAI 2021 NORA News

IJCAI 2020 NORA News

Women in AI NORA News

IJCAI 2015 Liverpool Postcard

Recent Talks:

Høst 2021


INF368 21H / Selected Topics in Artificial Intelligence: Language Processing Høst 2020


INF367 20H / Selected Topics in Artificial Intelligence: Learning Theory 


Graduate Student Supervision/Co-supervision


Cosimo Damiano Persia (PhD Student)

    • Research Topic: Learning Possibilistic Logic Theories

    • Institution: University of Bergen

    • Year: 2020 (on going)

Andrea Mazzullo (PhD Student)

    • Research Topic: Temporal Logic over Finite Traces

    • Institution: Free University of Bozen-Bolzano

    • Year: 2018 (on going)

Philip Turk (PhD Student)

    • Research Topic: Quantum Error Mitigation

    • Institution: University of Bergen

    • Year: 2021 (on going)

Cosimo Damiano Persia (Master Student)

    • Research Topic: Learning Query Inseparable Ontologies

    • Institution: Free University of Bozen-Bolzano

    • Year: 2018/2019

Ricardo Duarte (Master Student)

    • Thesis Title: Exact Learning of EL Ontologies

    • Institution: Dresden University of Technology

    • Year: 2017/2018


Topics for Master Students.

Neural Network Verification

Neural networks have been applied in many areas. However, any method based on generalizations may fail and this is by design. The question is how to deal with such failures. To limit them, one can define rules that a neural network should follow and devise strategies to verify whether the rules are obeyed. The main tasks of this project are to study an algorithm for learning rules formulated in propositional Horn, implement the algorithm, and apply it to verify neural networks.       


Queries and Concept Learning by Angluin (Machine Learning 1988)

Exact Learning: On the Boundary between Horn and CNF by Hermo and Ozaki (ACM TOCT 2020).

Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples by Weiss, Goldberg, Yahav (ICML 2018)


Knowledge Graph Embeddings

Knowledge graphs can be understood as labelled graphs whose nodes and edges are enriched with meta-knowledge, such as temporal validity, geographic coordinates, and provenance. Recent research in machine learning attempts to complete (or predict) facts in a knowledge graph by embedding entities and relations in low-dimensional vector spaces. The main tasks of this project are to study knowledge graph embeddings, study ways of integrating temporal validity in the geometrical model of a knowledge graph, implement and perform tests with an embedding that represents the temporal evolution of entities using their vector representations.


Translating Embeddings for Modeling Multi-relational Data by Bordes, Usunier, Garcia-Durán (NeurIPS 2013)

Temporally Attributed Description Logics by Ozaki, Krötzsch, Rudolph (Book chapter: Description Logic, Theory Combination, and All That 2019)

Attributed Description Logics: Reasoning on Knowledge Graphs by Krötzsch, Marx, Ozaki, Thost (ISWC 2017)


Decidability and Complexity of Learning 

Gödel showed in 1931 that, essentially, there is no consistent and complete set of axioms that is capable of modelling traditional arithmetic operations. Recently, Ben-David et al. defined a general learning model and showed that learnability in this model may not be provable using the standard axioms of mathematics. The main tasks of this project are to study Gödel's incompleteness theorems, the connection between these theorems and the theory of machine learning, and to investigate learnability and complexity classes in the PAC and the exact learning models.


Learnability can be undecidable by Ben-David, Hrubeš, Moran, Shpilka, Yehudayoff (Nature 2019)

On the Complexity of Learning Description Logic Ontologies by Ozaki (RW 2020)


Learning Ontologies via Queries

In artificial intelligence, ontologies have been used to represent knowledge about a domain of interest in a machine-processable format. However, designing and maintaining ontologies is an expensive process that often requires the interaction between ontology engineers and domain experts. The main tasks of this project are to study an algorithm for learning ontologies formulated in the ELH description logic, implement the algorithm, and evaluate it using an artificial oracle developed in the literature that simulates the domain expert.


Learning Query Inseparable ELH ontologies by Ozaki, Persia, Mazzullo (AAAI 2020)ExactLearner: A Tool for Exact Learning of EL Ontologies by Duarte, Konev, Ozaki (KR 2018)

Exact Learning of Lightweight Description Logic Ontologies by Konev, Lutz, Ozaki, Wolter (JMLR 2018)


Binarized Neural Networks

Binarized neural networks (BNNs) have recently attracted a lot of attention in the AI research community as a memory-efficient alternative to classical deep neural network models. In 2018, Narodytska et al. proposed an exact translation of BNNs into propositional logic. Using this translation, various properties such as robustness against adversarial attacks can be proved. The main tasks in this project are to study BNNs and the translation into propositional logic, implement an optimised version of the translation, and perform experiments verifying its correctness.


Binarized neural networks by Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv,Yoshua Bengio (NeurIPS-16)

Verifying Properties of Binarized Deep Neural Networks by Nina Narodytska, Shiva PrasadKasiviswanathan, Leonid Ryzhyk, Mooly Sagiv, Toby Walsh (AAAI-18)


Machine Ethics

Autonomous systems, such as self-driving cars, need to behave according to the environment in which they are embedded. However, ethical and moral behaviour is not universal and it is often the case that the underlying behaviour norms change among countries or groups of countries and a compromise among such differences needs to be considered.

The moral machines experiment (https://www.moralmachine.net/) exposed people to a series of moral dilemmas and asked people what should an autonomous vehicle do in each of the given situations. Researchers then tried to find similarities between the answers from the same region.

The main tasks of this project are to study the moral machine experiment, study and implement an algorithm for building compromises among different regions (or even people). We have developed a compromise building algorithm that works on behavioural norms represented as Horn clauses. Assume that each choice example from the moral machines experiment is behavioural norm represented as a Horn clause. The compromise algorithm is applied to these choices obtained from different people during the moral machines experiment. One of the goals of this project would be to determine how to (efficiently) compute compromises for groups of countries (e.g., the Nordic Countries and Scandinavia).




The Moral Machine experiment by Edmond Awad, Sohan Dsouza, Richard Kim, Jonathan Schulz, Joseph Henrich, Azim Shariff, Jean-François Bonnefon, and Iyad Rahwan (Nature 2018)


Advisors: Ana Ozaki, Marija Slavkovik



Own topic combining logic and learning


Contact: Ana Ozaki  

My record track, from 2014 until now, is of 1 book chapter and over 40 peer-reviewed journal, conference, and workshop publications. Most publications have the author list in alphabetical order.

DBLP Link: https://dblp.org/pers/o/Ozaki:Ana.html

  • Show author(s) 2020. Theorem Proving for Pointwise Metric Temporal Logic Over the Naturals via Translations. Journal of automated reasoning.
  • Show author(s) 2020. Provenance for the Description Logic ELHr. 8 pages.
  • Show author(s) 2020. On the Learnability of Possibilistic Theories. 7 pages.
  • Show author(s) 2020. On the Complexity of Learning Description Logic Ontologies. 17 pages.
  • Show author(s) 2020. On the Complexity of Learning Description Logic Ontologies.
  • Show author(s) 2020. Metric Temporal Description Logics with Interval-Rigid Names. ACM Transactions on Computational Logic.
  • Show author(s) 2020. Learning Query Inseparable ELH Ontologies. 8 pages.
  • Show author(s) 2020. Learning Description Logic Ontologies: Five Approaches. Where Do They Stand? Künstliche Intelligenz. 317-327.
  • Show author(s) 2020. Exact Learning: On the Boundary between Horn and CNF. ACM Transactions on Computation Theory.
  • Show author(s) 2020. 27th International Symposium on Temporal Representation and Reasoning, TIME 2020, September 23-25, 2020, Bozen-Bolzano, Italy. Schloss Dagstuhl - Leibniz-Zentrum für Informatik.
  • Show author(s) 2019. Temporally Attributed Description Logics.
  • Show author(s) 2019. Querying Attributed DL-Lite Ontologies Using Provenance Semirings. 8 pages.
  • Show author(s) 2019. Learning Ontologies with Epistemic Reasoning: The EL Case.
  • Show author(s) 2019. Enriching Ontology-based Data Access with Provenance.
  • Show author(s) 2019. Do You Need Infinite Time? 7 pages.
  • Show author(s) 2018. Preserving Constraints with the Stable Chase.
  • Show author(s) 2018. ExactLearner: A Tool for Exact Learning of EL Ontologies.
  • Show author(s) 2018. Exact learning of multivalued dependency formulas. Theoretical Computer Science.
  • Show author(s) 2018. Exact Learning of Lightweight Description Logic Ontologies. Journal of machine learning research.
  • Show author(s) 2018. Consequence-Based Axiom Pinpointing.
  • Show author(s) 2018. Attributed Description Logics: Reasoning on Knowledge Graphs.
  • Show author(s) 2017. Theorem Proving for Metric Temporal Logic over the Naturals.
  • Show author(s) 2017. Metric Temporal Description Logics with Interval-Rigid Names.
  • Show author(s) 2017. Attributed Description Logics: Ontologies for Knowledge Graphs.
  • Show author(s) 2016. On Metric Temporal Description Logics.
  • Show author(s) 2016. A Model for Learning Description Logic Ontologies Based on Exact Learning.
  • Show author(s) 2015. Schema.org as a Description Logi.
  • Show author(s) 2015. Exact Learning of Multivalued Dependencies.
  • Show author(s) 2014. Exact Learning of Lightweight Description Logic Ontologies.

More information in national current research information system (CRIStin)

Ana Ozaki is the principal investigator of the project Learning Description Logic Ontologies funded by RCN. The goal of this project is to study and develop new automated strategies for building ontologies. Ontologies can be understood as an unambiguous way of representing knowledge. The project has two main objectives. The first one is to extract knowledge from neural network models (NNs) by posing them queries. In this way, one can discover hidden rules encoded in NNs and represent them as an ontology. The second objective is to design ontology languages that approximate the expressivity of NNs and learn ontologies formulated in these enriched languages.

She is the leader of the Machine Learning Theory Work Package for the project "Machine learning for computational efficient predictions of long-term congestion patterns in large-scale transport systems" funded by RCN. The main goal of the project is to develop an AI-based sketch planning model that can reliably and quickly predict congestion patterns in complex transport systems for the present and future scenarios, varying traffic growth and road capacity.

She is a member of the Center for Data Science (CEDAS) at the University of Bergen.
Through the Momentum Program, she is currently working to expand her network of collaborators and to support research projects in her team.

Ana Ozaki has worked as the principal investigator of the project Apprendimento PAC di Ontologie in Logica Descrittiva (PACO) funded by Unibz. She has also collaborated with Montserrat Hermo within the project Modelos y metodos basados en grafos para la computacion en gran scala.