54 citations · 89 across the 16 of their papers we have counts for
18 papers
Small-World Communication Fabrics for Neuromorphic Multicore-SoCs
Sebastian Billaudelle, Christian Metzner, Jimmy Weber +7
As neuromorphic systems scale beyond a single core, inter-core event communication can become a dominant contributor to memory footprint, latency, and energy consumption. Biologica…
NORACL: Neurogenesis for Oracle-free Resource-Adaptive Continual Learning
Karthik Charan Raghunathan, Christian Metzner, Laura Kriener +1
In a continual learning setting, we require a model to be plastic enough to learn a new task and stable enough to not disturb previously learned capabilities. We argue that this di…
Real-time processing of analog signals on accelerated neuromorphic hardware
Yannik Stradmann, Johannes Schemmel, Mihai A. Petrovici +1
Sensory processing with neuromorphic systems is typically done by using either event-based sensors or translating input signals to spikes before presenting them to the neuromorphic…
Synchronization and semantization in deep spiking networks
Jonas Oberste-Frielinghaus, Anno C. Kurth, Julian Göltz +4
Recent studies have shown how spiking networks can learn complex functionality through error-correcting plasticity, but the resulting structures and dynamics remain poorly studied.…
mGRADE: Minimal Recurrent Gating Meets Delay Convolutions for Lightweight Sequence Modeling
Tristan Torchet, Christian Metzner, Karthik Charan Raghunathan +4
Multi-timescale sequence modeling relies on capturing both local fast dynamics and global slow context; yet, maintaining these capabilities under the strict memory constraints comm…
Quantizing Small-Scale State-Space Models for Edge AI
Leo Zhao, Tristan Torchet, Melika Payvand +2
State-space models (SSMs) have recently gained attention in deep learning for their ability to efficiently model long-range dependencies, making them promising candidates for edge-…
MINIMALIST: switched-capacitor circuits for efficient in-memory computation of gated recurrent units
Sebastian Billaudelle, Laura Kriener, Filippo Moro +2
Recurrent neural networks (RNNs) have been a long-standing candidate for processing of temporal sequence data, especially in memory-constrained systems that one may find in embedde…
The Role of Temporal Hierarchy in Spiking Neural Networks
Filippo Moro, Pau Vilimelis Aceituno, Laura Kriener +1
Spiking Neural Networks (SNNs) have the potential for rich spatio-temporal signal processing thanks to exploiting both spatial and temporal parameters. The temporal dynamics such a…
DelGrad: Exact event-based gradients for training delays and weights on spiking neuromorphic hardware
Julian Göltz, Jimmy Weber, Laura Kriener +5
Spiking neural networks (SNNs) inherently rely on the timing of signals for representing and processing information. Incorporating trainable transmission delays, alongside synaptic…
Backpropagation through space, time, and the brain
Benjamin Ellenberger, Paul Haider, Jakob Jordan +5
How physical networks of neurons, bound by spatio-temporal locality constraints, can perform efficient credit assignment, remains, to a large extent, an open question. In machine l…
ELiSe: Efficient Learning of Sequences in Structured Recurrent Networks
Laura Kriener, Kristin Völk, Kristin Spicher +6
Behavior can be described as a temporal sequence of actions driven by neural activity. To learn complex sequential patterns in neural networks, memories of past activities need to…
Gradient-based methods for spiking physical systems
Julian Göltz, Sebastian Billaudelle, Laura Kriener +5
Recent efforts have fostered significant progress towards deep learning in spiking networks, both theoretical and in silico. Here, we discuss several different approaches, includin…
Learning efficient backprojections across cortical hierarchies in real time
Kevin Max, Laura Kriener, Garibaldi Pineda García +4
Models of sensory processing and learning in the cortex need to efficiently assign credit to synapses in all areas. In deep learning, a known solution is error backpropagation, whi…
Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons
Paul Haider, Benjamin Ellenberger, Laura Kriener +3
The response time of physical computational elements is finite, and neurons are no exception. In hierarchical models of cortical networks each layer thus introduces a response lag.…
The Yin-Yang dataset
Laura Kriener, Julian Göltz, Mihai A. Petrovici
The Yin-Yang dataset was developed for research on biologically plausible error backpropagation and deep learning in spiking neural networks. It serves as an alternative to classic…
Fast and energy-efficient neuromorphic deep learning with first-spike times
Julian Göltz, Laura Kriener, Andreas Baumbach +9
For a biological agent operating under environmental pressure, energy consumption and reaction times are of critical importance. Similarly, engineered systems are optimized for sho…
A Mixed-Signal Structured AdEx Neuron for Accelerated Neuromorphic Cores
Syed Ahmed Aamir, Paul Müller, Gerd Kiene +5
Here we describe a multi-compartment neuron circuit based on the Adaptive-Exponential I&F (AdEx) model, developed for the second-generation BrainScaleS hardware. Based on an existi…
An Accelerated Analog Neuromorphic Hardware System Emulating NMDA- and Calcium-Based Non-Linear Dendrites
Johannes Schemmel, Laura Kriener, Paul Müller +1
This paper presents an extension of the BrainScaleS accelerated analog neuromorphic hardware model. The scalable neuromorphic architecture is extended by the support for multi-comp…