Max Welling
Professor of Machine Learning, University of Amsterdam; Chief AI Officer, CuspAI
Builder The claim is about what the hardware does, and the philosophy is left open
Max Welling is a professor of machine learning at the University of Amsterdam and one of the builders of two lines this site follows. The first is AKOrN, Artificial Kuramoto Oscillatory Neurons, which he co-authored with Takeru Miyato, Sindy Löwe and Andreas Geiger (ICLR 2025, oral). AKOrN replaces threshold units with Kuramoto oscillators inside deep networks, and it supports fully connected, convolutional and attention coupling. The project’s own binding layer uses that mechanism, with five module oscillators integrated through the update rule in the public research repo (the Brain Waves Console runs the same equations in the browser). The second line is Neural Wave Machines, co-authored with T. Anderson Keller (his profile), where locally coupled oscillatory RNNs carry sequences through traveling waves in their hidden state.
Welling’s broader research sits at the geometry of learning, from variational inference and Bayesian methods to geometric deep learning and graph neural networks, and the oscillatory work is where that geometry meets neural dynamics. For consciousness research his relevance is concrete. AKOrN is a working, inspectable implementation of the Kuramoto binding idea, which is why a 2026 cortex review cites it beside the neural wave models, and why this project chose it as the mechanism its workspace binding layer runs.
Known for. Co-author of Artificial Kuramoto Oscillatory Neurons (Miyato, Löwe, Geiger and Welling, ICLR 2025), Neural Wave Machines with T. Anderson Keller (ICML 2023), and foundational work on variational inference, geometric deep learning and graph neural networks
Coverage on this site
- Artificial Kuramoto Oscillatory Neurons (AKOrN), What They Bind and What Hardware Can Run Them October 2026
Related researchers
- Takeru MiyatoPreferred Networks, Inc.; PhD student, Autonomous Vision Group, University of TübingenFirst author of Artificial Kuramoto Oscillatory Neurons (ICLR 2025 oral), and earlier work on spectral normalization and adversarial training methods for semi-supervised learning
- Andreas GeigerProfessor of Computer Science, University of Tübingen, head of the Autonomous Vision Group, Tübingen AI CenterCo-author of Artificial Kuramoto Oscillatory Neurons (Miyato, Löwe, Geiger and Welling, ICLR 2025), whose code is released by his Autonomous Vision Group, and the KITTI benchmark for autonomous driving
- Navid Anjum AaditDepartment of Electrical Engineering, Stanford University (present address); previously University of California, Santa BarbaraFirst author of the sparse Ising machine on FPGAs (Nature Electronics, 2022) and of the programmable probabilistic computer with one million p-bits (arXiv 2606.25313, 2026)
- Vikas AgnihotriIndependent Aerospace and Neuromorphic Systems ResearcherNeuromorphic Satellite Intelligence framework, radiation-induced energy overhead model for spiking neural hardware, constrained on-orbit STDP
- James B. AimoneCenter for Computing Research, Sandia National LaboratoriesNeuromorphic algorithms, adult Drosophila FlyWire connectome simulation on Intel Loihi 2, adult hippocampal neurogenesis modeling
- Matt AngleParadromicsFounder and CEO of Paradromics, developer of the Connexus Direct Data Interface high-data-rate brain-computer interface
Max Welling is listed with the other builders, who hold that the claim is about what the hardware does, and the philosophy is left open. The positions themselves are set out in the index of consciousness theories. Every researcher covered on this site is indexed in the directory of consciousness researchers.