# Neuro-Symbolic Integration

##### Winter 


##### (in German: Neuro-Symbolic Integration )

<table bgcolor="#7FB3D9" border="1" id="bkmrk-%5Btitle%5D" style="width: 100%; border-collapse: collapse; border-width: 1px; border-style: none;"><colgroup><col style="width: 100%;"></col></colgroup><tbody><tr style="background-color: rgb(235, 243, 249);"><td>##### <span style="color: rgb(0, 104, 180);">**Module-ID:** </span><span style="color: rgb(0, 104, 180);">**FIN-INF-0** </span>

</td></tr></tbody></table>

<table bgcolor="#7FB3D9" border="1" id="bkmrk-" style="border-collapse: collapse; width: 100%;"><colgroup><col style="width: 14.2515%;"></col><col style="width: 14.2515%;"></col><col style="width: 13.061%;"></col><col style="width: 15.442%;"></col><col style="width: 14.2515%;"></col><col style="width: 14.2515%;"></col><col style="width: 14.2515%;"></col></colgroup><tbody><tr><td class="align-center" style="border: 5px solid rgb(255, 255, 255);"><span style="color: rgb(61, 61, 61);">**Abbreviation**</span>

<span style="color: rgb(61, 61, 61);">NeSy </span>

</td><td class="align-center" style="border: 5px solid rgb(255, 255, 255);"><span style="color: rgb(61, 61, 61);">**Credit Points**</span>

<span style="color: rgb(61, 61, 61);">6 </span>

</td><td class="align-center" style="border: 5px solid rgb(255, 255, 255);"><span style="color: rgb(61, 61, 61);">**Semester**</span>

<span style="color: rgb(61, 61, 61);">Winter </span>

</td><td class="align-center" style="border: 5px solid rgb(255, 255, 255);"><span style="color: rgb(61, 61, 61);">**Term**</span>

<span style="color: #3d3d3d;">1. 

</span>

</td><td class="align-center" style="border: 5px solid rgb(255, 255, 255);">**<span style="color: rgb(61, 61, 61);">Duration</span>**

<span style="color: rgb(61, 61, 61);">1 Semester </span>

</td><td class="align-center" style="border: 5px solid rgb(255, 255, 255);"><span style="color: rgb(61, 61, 61);">**Language**</span>

<span style="color: rgb(61, 61, 61);">english</span>

</td><td class="align-center" style="border: 5px solid rgb(255, 255, 255);"><span style="color: rgb(61, 61, 61);">**Level**</span>

<span style="color: rgb(61, 61, 61);">Master </span>

</td></tr></tbody></table>

<table border="1" id="bkmrk-verantwortung%3A-verwe" style="border-collapse: collapse; width: 100%; height: 124.8px; border-width: 1px; border-style: none;"><colgroup><col style="width: 24.7879%;"></col><col style="width: 75.2121%;"></col></colgroup><tbody><tr style="height: 35.4px;"><td style="height: 35.4px;">**Link:**</td><td style="height: 35.4px;">[ LSF](https://lsf.ovgu.de/qislsf/rds?state=wsearchv&search=1&subdir=veranstaltung&veranstaltung.semester=20262&veranstaltung.dtxt=Neuro-Symbolic+Integration&P_start=0&P_anzahl=30&P.sort=veranstaltung.dtxt&_form=display "Neuro-Symbolic Integration")</td></tr><tr><td>**Limited accessability:**</td><td>true </td></tr><tr style="height: 29.8px;"><td style="height: 29.8px;">**Responsibility:**</td><td style="height: 29.8px;">Martin Glauer </td></tr><tr style="height: 29.8px;"><td style="height: 29.8px;">**Lecturer:**</td><td style="height: 29.8px;">Martin Glauer </td></tr><tr><td>**Classes:**</td><td>- Lectures
- Exercise Classes

 </td></tr><tr style="height: 29.8px;"><td style="height: 29.8px;">**Applicability in curriculum:**</td><td style="height: 29.8px;">- M.Sc. INF: Informatik  
- M.Sc. INF: Informatik Wahlpflicht (SPO 2027)  
- M.Sc. INGINF: Informatik  
- M.Sc. WIF: Informatik  
- M.Sc. WIF: Informatik Wahlpflicht (SPO 2027)  
- M.Sc. DKE: Learning Methods and Models for Data Science  
- M.Sc. DE: Methoden der Informatik  
- M.Sc. DE: Informatik Wahlpflicht (SPO 2027)  
- M.Sc. VC: Computer Science  
- M.Sc. VC: Computer Science (SPO 2027)  
  
</td></tr></tbody></table>

**Intended learning outcomes:** Die Absolvent:innen vertiefen die Inhalte der Lehrveranstaltungen Logik und Intelligente Systeme, indem sie lernen, wie diese zu Neuro-Symbolischen Methoden kombiniert werden können. Hierfür werden neuste Forschungsinhalte aus diesem Gebiet vorgestellt und hinsichtlich der Eignung bestimmter Problemstellungen untersucht. Somit lernen Absolvent:innen komplexe Aufgaben aus der Schnittstelle von Anwendung und Forschung selbstständig zu bewältigen. In den Übungen werden auch offene Aufgaben gestellt, bei denen die eigenen Ergebnisse erklärt und kritisch bewertet und ggf alternative Ansätze vorgeschlagen werden sollen. Die Teilnehmenden können so eigene Ideen einbringen und erlangen detailliertes und kritisches Verständnis der Methoden der neuro-symbolischen Integration.

**Content:**

- (Fuzzy) Logic
- Neuro-Symbolic Integration nach von Hamelen
- Propositional Program Extraction (Arthur, KBANN)
- Cognitive architectures (CLARION)
- Logic Tensor Networks
- Logical Neural Networks
- Graph Neural Networks
- Ontology-based Training

**Workload:** Total: 180 h

- Weekly lecture (2 SWS = 28 h) 
    - Follow-up work (20 h)
- Weekly exercise session (2 SWS = 28 h) 
    - Completing assignments (84 h)
    - Follow-up work (20 h)

  
<table border="1" id="bkmrk-studien-%2Fpr%C3%BCfungslei" style="border-collapse: collapse; width: 100%;"><colgroup><col style="width: 32.0641%;"></col><col style="width: 34.9204%;"></col><col style="width: 33.0155%;"></col></colgroup><tbody><tr><td>**Pre-examination requirements:**</td><td>**Type of examination:**</td><td>**Teaching method / lecture hours per week (SWS):**</td></tr><tr><td>- Active participations during the exercise sessions
- Voting for exercise tasks

</td><td>Schriftliche Prüfung/Klausur bzw. elektronische Prüfung (written exam)

</td><td>Lecture (2 SWS) Exercise (2 SWS)

</td></tr></tbody></table>

<table border="1" id="bkmrk-voraussetzungen-nach" style="font-family: var(--font-body); font-size: 14px; width: 100%;"><colgroup><col style="width: 50%;"></col><col style="width: 50%;"></col></colgroup><tbody><tr><td>**Prerequisites according to examination regulations:**</td><td>**Recommended prerequisites:**</td></tr><tr><td>keine

</td><td>Logik/Logic Intelligente Systeme/Intelligent Systems Deep Learning Programming experience (e.g. in Python)

</td></tr></tbody></table>

<table border="1" id="bkmrk-medienformen%3A-litera" style="border-collapse: collapse; width: 100%;"><colgroup><col style="width: 50%;"></col><col style="width: 50%;"></col></colgroup><tbody><tr><td>**Media:**</td><td>**Literature:**</td></tr><tr><td></td><td>- **Books**
    - P. Hitzler and M. K. Sarker (eds.): [Neuro-Symbolic Artificial Intelligence](https://lhmdb.gbv.de/DB=1/XMLPRS=N/PPN?PPN=1793806039), IOS Press, 2022
    - Artur S. d'Avila Garcez, Krysia Broda, Dov M. Gabbay: [Neural-symbolic learning systems - foundations and applications](https://link.springer.com/book/10.1007/978-1-4471-0211-3). Perspectives in neural computing, Springer 2002 [PDF](http://iks.cs.ovgu.de/~till/Neural-Symbolic-Learning-Systems.pdf)
    - Garcez A, Lamb LC, Gabbay DM. [Neural-symbolic cognitive reasoning](https://link.springer.com/book/10.1007/978-3-540-73246-4). Springer; 2009. Cognitive  
        Technologies.
    - Hammer B, Hitzler P, editors. [Perspectives of neural-symbolic integration](https://link.springer.com/book/10.1007/978-3-540-73954-8). Springer; 2007.
- **Survey papers**
    - Michael van Bekkum, Maaike de Boer, Frank van Harmelen, André Meyer-Vitali, Annette ten Teije: [Modular design patterns for hybrid learning and reasoning systems.](https://link.springer.com/article/10.1007/s10489-021-02394-3) Appl. Intell. 51(9): 6528-6546 (2021)
    - Md. Kamruzzaman Sarker, Lu Zhou, Aaron Eberhart, Pascal Hitzler: [Neuro-Symbolic Artificial Intelligence: Current Trends](https://arxiv.org/abs/2105.05330). CoRR abs/2105.05330 (2021)
    - Artur d'Avila Garcez, Luís C. Lamb: [Neurosymbolic AI: The 3rd Wave](https://arxiv.org/abs/2012.05876). CoRR abs/2012.05876 (2020)
    - Tarek R. Besold, et al.: [Neural-Symbolic Learning and Reasoning: A Survey and Interpretation.](https://arxiv.org/abs/1711.03902) CoRR abs/1711.03902 (2017)
    - Marra G, Dumancic S, Manhaeve R, et al. [From statistical relational to neural symbolic artificial in-](https://arxiv.org/abs/2108.11451)  
        [telligence: a survey](https://arxiv.org/abs/2108.11451). CoRR abs/2108.11451 (2021)
    - Grady Booch et al.: [Thinking Fast and Slow in AI](https://ojs.aaai.org/index.php/AAAI/article/view/17765). AAAI 2021: 15042-15046 (2021)
- **Specific approaches**
    - Samy Badreddine, Artur d'Avila Garcez, Luciano Serafini, Michael Spranger: [Logic Tensor Networks](https://www.sciencedirect.com/science/article/abs/pii/S0004370221002009). Artif. Intell. 303: 103649 (2022)
    - Ryan Riegel et al.: [Logical Neural Networks](https://arxiv.org/abs/2006.13155). CoRR abs/2006.13155 (2020)
    - Honghua Dong et al.: [Neural Logic Machines](https://arxiv.org/abs/1904.11694). ICLR (Poster) 2019. Also: CoRR abs/1904.11694
    - Matthieu Zimmer et al.: [Differentiable Logic Machines](https://arxiv.org/abs/2102.11529). CoRR abs/2102.11529 (2021)
    - F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini. “[The graph neural network model](https://persagen.com/files/misc/scarselli2009graph.pdf).” In: IEEE transactions on neural networks 20.1 (2008), pp. 61–80.
    - J. Chen, P. Hu, E. Jiménez-Ruiz, O. M. Holter, D. Antonyrajah, and I. Horrocks. “[OWL2Vec\*: embedding of OWL ontologies](https://link.springer.com/article/10.1007/s10994-021-05997-6).” In: Mach. Learn. 110.7 (2021), pp. 1813–1845.
    - Aws Albarghouthi: [Introduction to Neural Network Verification](https://verifieddeeplearning.com/).

  
</td></tr></tbody></table>

**Comments:**