idw – Informationsdienst Wissenschaft

Nachrichten, Termine, Experten

Grafik: idw-Logo
Science Video Project
idw-Abo

idw-News App:

AppStore

Google Play Store



Instance:
Share on: 
03/28/2025 18:41

Artificial neurons organize themselves

Dr. Manuel Maidorn Presse- und Öffentlichkeitsarbeit
Max-Planck-Institut für Dynamik und Selbstorganisation

    Novel artificial neurons learn independently and are more strongly modeled on their biological counterparts. A team of researchers from the Göttingen Campus Institute for Dynamics of Biological Networks (CIDBN) at the University of Göttingen and the Max Planck Institute for Dynamics and Self-Organization (MPI-DS) has programmed these infomorphic neurons and constructed artificial neural networks from them. The special feature is that the individual artificial neurons learn in a self-organized way and draw the necessary information from their immediate environment in the network. The results were published in PNAS.

    Both, human brain and modern artificial neural networks are extremely powerful. At the lowest level, the neurons work together as rather simple computing units. An artificial neural network typically consists of several layers composed of individual neurons. An input signal passes through these layers and is processed by artificial neurons in order to extract relevant information. However, conventional artificial neurons differ significantly from their biological models in the way they learn. While most artificial neural networks depend on overarching coordination outside the network in order to learn, biological neurons only receive and process signals from other neurons in their immediate vicinity in the network. Biological neural networks are still far superior to artificial ones in terms of both, flexibility and energy efficiency.

    The new artificial neurons, known as infomorphic neurons, are capable of learning independently and self-organized among their neighboring neurons. This means that the smallest unit in the network has to be controlled no longer from the outside, but decides itself which input is relevant and which is not. In developing the infomorphic neurons, the team was inspired by the way the brain works, especially by the pyramidal cells in the cerebral cortex. These also process stimuli from different sources in their immediate environment and use them to adapt and learn. The new artificial neurons pursue very general, easy-to-understand learning goals: “We now directly understand what is happening inside the network and how the individual artificial neurons learn independently”, emphasizes Marcel Graetz from CIDBN.

    By defining the learning objectives, the researchers enabled the neurons to find their specific learning rules themselves. The team focused on the learning process of each individual neuron. They applied a novel information-theoretic measure to precisely adjust whether a neuron should seek more redundancy with its neighbors, collaborate synergistically, or try to specialize in its own part of the network's information. “By specializing in certain aspects of the input and coordinating with their neighbors, our infomorphic neurons learn how to contribute to the overall task of the network”, explains Valentin Neuhaus from MPI-DS. With the infomorphic neurons, the team is not only developing a novel method for machine learning, but is also contributing to a better understanding of learning in the brain.


    Original publication:

    https://www.pnas.org/doi/10.1073/pnas.2408125122


    More information:

    https://www.ds.mpg.de/4079302/250328_artificial_neurons


    Images

    Living neurons receive signals from different sources, process them and pass an output signal on to other neurons (left). In the artificial neuron model, this information processing can be described and improved by a learning objective (right).
    Living neurons receive signals from different sources, process them and pass an output signal on to ...

    Andreas Schneider, MPI-DS


    Criteria of this press release:
    Journalists
    Physics / astronomy
    transregional, national
    Research results
    English


     

    Living neurons receive signals from different sources, process them and pass an output signal on to other neurons (left). In the artificial neuron model, this information processing can be described and improved by a learning objective (right).


    For download

    x

    Help

    Search / advanced search of the idw archives
    Combination of search terms

    You can combine search terms with and, or and/or not, e.g. Philo not logy.

    Brackets

    You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).

    Phrases

    Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.

    Selection criteria

    You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).

    If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).