624 citations · 1.4k across the 27 of their papers we have counts for
27 papers
Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning
Julian Gutheil, Simon Hitzginger, Robert Legenstein
Winner-take-all (WTA) networks constitute a central circuit motif in cortical networks of the brain. In addition, WTA-like activations are abundant in modern deep learning models i…
A Scalable Hybrid Training Approach for Recurrent Spiking Neural Networks
Maximilian Baronig, Yeganeh Bahariasl, Ozan Özdenizci +1
Recurrent spiking neural networks (RSNNs) can be implemented very efficiently in neuromorphic systems. Nevertheless, training of these models with powerful gradient-based learning…
Adversarially Robust Spiking Neural Networks with Sparse Connectivity
Mathias Schmolli, Maximilian Baronig, Robert Legenstein +1
Deployment of deep neural networks in resource-constrained embedded systems requires innovative algorithmic solutions to facilitate their energy and memory efficiency. To further e…
Privacy-Aware Lifelong Learning
Ozan Özdenizci, Elmar Rueckert, Robert Legenstein
Lifelong learning algorithms enable models to incrementally acquire new knowledge without forgetting previously learned information. Contrarily, the field of machine unlearning foc…
Advancing Spatio-Temporal Processing in Spiking Neural Networks through Adaptation
Maximilian Baronig, Romain Ferrand, Silvester Sabathiel +1
Implementations of spiking neural networks on neuromorphic hardware promise orders of magnitude less power consumption than their non-spiking counterparts. The standard neuron mode…
Adaptive Robotic Arm Control with a Spiking Recurrent Neural Network on a Digital Accelerator
Alejandro Linares-Barranco, Luciano Prono, Robert Lengenstein +2
With the rise of artificial intelligence, neural network simulations of biological neuron models are being explored to reduce the footprint of learning and inference in resource-co…
Learning-to-learn enables rapid learning with phase-change memory-based in-memory computing
Thomas Ortner, Horst Petschenig, Athanasios Vasilopoulos +7
There is a growing demand for low-power, autonomously learning artificial intelligence (AI) systems that can be applied at the edge and rapidly adapt to the specific situation at d…
Adversarially Robust Spiking Neural Networks Through Conversion
Ozan Özdenizci, Robert Legenstein
Spiking neural networks (SNNs) provide an energy-efficient alternative to a variety of artificial neural network (ANN) based AI applications. As the progress in neuromorphic comput…
Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models
Ozan Özdenizci, Robert Legenstein
Image restoration under adverse weather conditions has been of significant interest for various computer vision applications. Recent successful methods rely on the current progress…
Memory-enriched computation and learning in spiking neural networks through Hebbian plasticity
Thomas Limbacher, Ozan Özdenizci, Robert Legenstein
Memory is a key component of biological neural systems that enables the retention of information over a huge range of temporal scales, ranging from hundreds of milliseconds up to y…
Many-Joint Robot Arm Control with Recurrent Spiking Neural Networks
Manuel Traub, Robert Legenstein, Sebastian Otte
In the paper, we show how scalable, low-cost trunk-like robotic arms can be constructed using only basic 3D-printing equipment and simple electronics. The design is based on unifor…
Cortical oscillations implement a backbone for sampling-based computation in spiking neural networks
Agnes Korcsak-Gorzo, Michael G. Müller, Andreas Baumbach +7
Being permanently confronted with an uncertain world, brains have faced evolutionary pressure to represent this uncertainty in order to respond appropriately. Often, this requires…
Embodied Synaptic Plasticity with Online Reinforcement learning
Jacques Kaiser, Michael Hoff, Andreas Konle +8
The endeavor to understand the brain involves multiple collaborating research fields. Classically, synaptic plasticity rules derived by theoretical neuroscientists are evaluated in…
Fast learning synapses with molecular spin valves via selective magnetic potentiation
Alberto Riminucci, Robert Legenstein
We studied LSMO/Alq3/AlOx/Co molecular spin valves in view of their use as synapses in neuromorphic computing. In neuromorphic computing, the learning ability is embodied in specif…
Efficient Reward-Based Structural Plasticity on a SpiNNaker 2 Prototype
Yexin Yan, David Kappel, Felix Neumaerker +7
Advances in neuroscience uncover the mechanisms employed by the brain to efficiently solve complex learning tasks with very limited resources. However, the efficiency is often lost…
Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets
Guillaume Bellec, Franz Scherr, Elias Hajek +3
The way how recurrently connected networks of spiking neurons in the brain acquire powerful information processing capabilities through learning has remained a mystery. This lack o…
Long short-term memory and learning-to-learn in networks of spiking neurons
Guillaume Bellec, Darjan Salaj, Anand Subramoney +2
Recurrent networks of spiking neurons (RSNNs) underlie the astounding computing and learning capabilities of the brain. But computing and learning capabilities of RSNN models have…
Deep Rewiring: Training very sparse deep networks
Guillaume Bellec, David Kappel, Wolfgang Maass +1
Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning ru…
A probabilistic model for learning in cortical microcircuit motifs with data-based divisive inhibition
Robert Legenstein, Zeno Jonke, Stefan Habenschuss +1
Previous theoretical studies on the interaction of excitatory and inhibitory neurons proposed to model this cortical microcircuit motif as a so-called Winner-Take-All (WTA) circuit…
Feedback inhibition shapes emergent computational properties of cortical microcircuit motifs
Zeno Jonke, Robert Legenstein, Stefan Habenschuss +1
Cortical microcircuits are very complex networks, but they are composed of a relatively small number of stereotypical motifs. Hence one strategy for throwing light on the computati…
A dynamic connectome supports the emergence of stable computational function of neural circuits through reward-based learning
David Kappel, Robert Legenstein, Stefan Habenschuss +2
Synaptic connections between neurons in the brain are dynamic because of continuously ongoing spine dynamics, axonal sprouting, and other processes. In fact, it was recently shown…
Neuromorphic Hardware In The Loop: Training a Deep Spiking Network on the BrainScaleS Wafer-Scale System
Sebastian Schmitt, Johann Klaehn, Guillaume Bellec +22
Emulating spiking neural networks on analog neuromorphic hardware offers several advantages over simulating them on conventional computers, particularly in terms of speed and energ…
Pattern representation and recognition with accelerated analog neuromorphic systems
Mihai A. Petrovici, Sebastian Schmitt, Johann Klähn +33
Despite being originally inspired by the central nervous system, artificial neural networks have diverged from their biological archetypes as they have been remodeled to fit partic…
A model for structured information representation in neural networks
Michael G. Müller, Christos H. Papadimitriou, Wolfgang Maass +1
Humans possess the capability to reason at an abstract level and to structure information into abstract categories, but the underlying neural processes have remained unknown. Exper…