Nature-Inspired Machine Intelligence (NIMI)2021-04-15T19:08:56+02:00
Full 2
Nature-Inspired Machine Intelligence
Full 2
Nature-Inspired Machine Learning


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:

  1. The power efficiency of AI systems is very low — a brain just needs a few watts compared to supercomputer/clouds, and
  2. 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
  3. Systems often lack the robustness and lifelong learning abilities we see in nature

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

Richard P. Feynman

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 


Dr. Sahar Vahdati
Dr. Sahar VahdatiGroup Lead
at NIMI | InfAI
Mojtaba Nayyeri
Mojtaba NayyeriResearch Associate
at NIMI | InfAI
Mirza Mohtashim Alam
Mirza Mohtashim AlamResearch Assistant
at NIMI | InfAI


Link Prediction using Numerical Weights for Knowledge Graph Completion within the Scholarly Domain

By , , , , , , , , , |Dezember 11th, 2020|

Abstract Knowledge graphs (KGs) are widely used for modeling scholarly communication, informing scientometric analysis, and supporting a variety of intelligent services to explore the literature and predict research dynamics. However, they often suffer from incompleteness (eg, missing affiliations, references, research topics), which ends up reducing the scope and quality of the resulting analysis. This issue is usually tackled by computing knowledge graph embeddings (KGEs) [...]

5* Knowledge Graph Embeddings with Projective Transformations

By , , , |Juni 8th, 2020|

Abstract Performing link prediction using knowledge graph embedding (KGE) models is a popular approach for knowledge graph completion. Such link predictions are performed by measuring the likelihood of links in the graph via a transformation function that maps nodes via edges into a vector space. Since the complex structure of the real world is reflected in multi-relational knowledge graphs, the transformation functions need to [...]




Nature-Inspired Machine Intelligence(NIMI)


Schnorrstraße 70

01069 Dresden Germany

Partner(s) of NIMI

Copyright 2021 InfAI | All Rights Reserved

Nach oben