Home2024-04-09T09:16:48+02:00

NIMI

Nature-Inspired Machine Intelligence

Nature-Inspired Machine Intelligence

Nature, and all that it encompasses, has influenced computer science, in particular Artificial Intelligence, from its inception. Many effective tools, mechanisms, processes, algorithms, methods, and systems have been proposed inspired by nature. For example, Neural Networks are roughly inspired by the cognitive brain function, Genetic Algorithms are inspired by evolution and the survival of the fittest, and Artificial Immune Systems are inspired by their biological equivalents. Further examples include swarm or collective approaches, that are inspired by colonies of insects and birds. Current AI methods have the following weaknesses:

  • The power efficiency of AI systems is very low — a brain just needs a few watts compared to supercomputer/clouds
  • Systems are often low-level end-to-end and cannot incorporate knowledge very well, however, most of the intelligence of humans comes from building layer after layer of knowledge
  • Systems often lack the robustness and lifelong learning abilities we see in nature

Research in machine intelligence inspired by natural science can result in innovations that address those weaknesses. The main activities of the group and planned research directions will focus on existing concepts in nature and natural science including intelligent systems such as the human brain. Within the group, the following focal points will be addressed in the next years:

  • Nature in Knowledge Representation — Representation Learning and Reasoning
  • Natural Sciences in Knowledge Discovery and Data Mining with Embeddings/Neural Networks
  • Human Mind in Deep Neural-symbolic Learning and Reasoning
  • Nature-inspired Neural Networks
  • Applications of Machine Intelligence for Social good, Scholarly Communication and Education, Health, and Nature and Environmental Studies

Cross Organization NIMI

The Nature-Inspired Machine Intelligence (NIMI) research group, led by Dr. Sahar Vahdati , is a virtual research group with researchers from Scads.AI at TU Dresden and the Institute for Applied Computer Science (InfAI), and Leibniz University of Hannover, as well as external researchers. This research group works on machine learning, representation learning, knowledge graphs. and reinforcement learning.

Research Areas

Exploring the frontiers of artificial intelligence, our team specializes in advanced machine learning solutions to address real-world challenges.

Latest Projects

NIMI coordinates, and contributes to several projects. Main funding sources are EU projects, BMBF and DFG proposals. Here we present the projects in which NIMI is active as core AI partner

e-VITA

The overall objective of e-VITA is to improve well-being in older adults in Europe and Japan  and thereby promote active and healthy ageing, contribute to independent living, and reduce risks of social exclusion of older adults. [...]

CALLISTO

Artificial Intelligence (AI) is already part of our lives and is extensively entering the space sector to offer value-added Earth Observation (EO) products and services. Copernicus data and other georeferenced data sources are often [...]

IntelliLung

Intensive care patients with acute respiratory failure usually need support of lung function, which is accomplished with mechanical ventilation and, in most severe cases, extracorporeal gas exchange. Although mechanical ventilation is a life-saving therapy, it [...]

Selected Publication

This is a handpicked selection of three research papers, constantly refreshed to highlight our team’s newest and most innovative contributions to the ever-evolving world of science and technology.

Language Models as Controlled Natural Language Semantic Parsers for  Knowledge Graph Question Answering

Lehmann, Jens; Ferré, Sébastien; Vahdati, Sahar

Language Models as Controlled Natural Language Semantic Parsers for Knowledge Graph Question Answering Proceedings Article

In: Gal, Kobi; Nowé, Ann; Nalepa, Grzegorz J.; Fairstein, Roy; Radulescu, Roxana (Ed.): ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland - Including 12th Conference on Prestigious Applications of Intelligent Systems (PAIS 2023), pp. 1348–1356, IOS Press, 2023.

BibTeX | Tags: SelectedPublication | Links:

5* Knowledge Graph Embeddings with Projective Transformations

Nayyeri, Mojtaba; Vahdati, Sahar; Aykul, Can; Lehmann, Jens

5* Knowledge Graph Embeddings with Projective Transformations Proceedings Article

In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pp. 9064–9072, AAAI Press, 2021.

BibTeX | Tags: SelectedPublication | Links:

Unveiling Scholarly Communities over Knowledge Graphs

Vahdati, Sahar; Palma, Guillermo; Nath, Rahul Jyoti; Lange, Christoph; Auer, Sören; Vidal, Maria-Esther

Unveiling Scholarly Communities over Knowledge Graphs Journal Article

In: CoRR, vol. abs/1807.06816, 2018.

BibTeX | Tags: SelectedPublication | Links:

„The job of a scientist is to listen carefully to nature, not to tell nature how to behave.“

Richard P. Feynman

Our Partners

The core of NIMI research group is based at ScaDS.AI center at TU Dresden – but it is a hub of international and cross-institutional collaboration. We are technical and AI partner of several EU projects and work with research partners worldwide, reflecting our global reach. Additionally, we maintain strong ties with Leipzig University, Hannover University, and InfAI, fostering a rich network of expertise and knowledge across organizations.

Join Our Team!

We support students who want to apply for DAAD or CSC and similar doctoral grants.

Go to Top