arXiv subjects

Thomas Nowotny

Publications and source records attributed to Thomas Nowotny.

At least 19 recordsLinked to original sources

arXiv2025

Space as Time Through Neuron Position Learning

Biological neural networks exist in physical space where distance influences communication delays: a fundamental coupling between space and time absent in most artificial neural networks. While recent work has separately explored spatial embeddings and learnable synaptic delays in spiking neural networks, we unify these approaches through a novel neuron position learning algorithm where delays relate to the Euclidean distances between neurons. We derive gradients with respect to neuron positions and demonstrate that this biologically-motivated constraint acts as an inductive bias: networks trained on temporal classification tasks spontaneously self-organize into local, clustered topologies and a modular, efficiently wired structure emerges if connection costs are distance-dependent. Remarkably, we observe functional specialization aligned with spatial clustering without explicitly enforcing it. These findings lay the groundwork for networks in which space and time are intrinsically coupled, offering new avenues for mechanistic interpretability, biologically inspired modelling, and efficient implementations.

cs.NE↗

arXiv2025

FeNN-DMA: A RISC-V SoC for SNN acceleration

Spiking Neural Networks (SNNs) are a promising, energy-efficient alternative to standard Artificial Neural Networks (ANNs) and are particularly well-suited to spatio-temporal tasks such as keyword spotting and video classification. However, SNNs have a much lower arithmetic intensity than ANNs and are therefore not well-matched to standard accelerators like GPUs and TPUs. Field Programmable Gate Arrays (FPGAs) are designed for such memory-bound workloads, and here we present a novel, fully-programmable RISC-V-based system-on-chip (FeNN-DMA), tailored to simulating SNNs on modern UltraScale+ FPGAs. We show that FeNN-DMA has comparable resource usage and energy requirements to state-of-the-art fixed-function SNN accelerators, yet it supports more complex neuron models and network topologies, and can simulate up to 16 thousand neurons and 256 million synapses per core. Using this functionality, we demonstrate state-of-the-art classification accuracy on the Spiking Heidelberg Digits, Neuromorphic MNIST and Braille tactile classification tasks.

cs.NE↗

arXiv2025

A flexible framework for structural plasticity in GPU-accelerated sparse spiking neural networks

The majority of research in both training Artificial Neural Networks (ANNs) and modeling learning in biological brains focuses on synaptic plasticity, where learning equates to changing the strength of existing connections. However, in biological brains, structural plasticity - where new connections are created and others removed - is also vital, not only for effective learning but also for recovery from damage and optimal resource usage. Inspired by structural plasticity, pruning is often used in machine learning to remove weak connections from trained models to reduce the computational requirements of inference. However, the machine learning frameworks typically used for backpropagation-based training of both ANNs and Spiking Neural Networks (SNNs) are optimized for dense connectivity, meaning that pruning does not help reduce the training costs of ever-larger models. The GeNN simulator already supports efficient GPU-accelerated simulation of sparse SNNs for computational neuroscience and machine learning. Here, we present a new flexible framework for implementing GPU-accelerated structural plasticity rules and demonstrate this first using the e-prop supervised learning rule and DEEP R to train efficient, sparse SNN classifiers and then, in an unsupervised learning context, to learn topographic maps. Compared to baseline dense models, our sparse classifiers reduce training time by up to 10x while the DEEP R rewiring enables them to perform as well as the original models. We demonstrate topographic map formation in faster-than-realtime simulations, provide insights into the connectivity evolution, and measure simulation speed versus network size. The proposed framework will enable further research into achieving and maintaining sparsity in network structure and neural communication, as well as exploring the computational benefits of sparsity in a range of neuromorphic applications.

cs.NE↗

arXiv2025

A Complete Pipeline for deploying SNNs with Synaptic Delays on Loihi 2

Spiking Neural Networks are attracting increased attention as a more energy-efficient alternative to traditional Artificial Neural Networks for edge computing. Neuromorphic computing can significantly reduce energy requirements. Here, we present a complete pipeline: efficient event-based training of SNNs with synaptic delays on GPUs and deployment on Intel's Loihi 2 neuromorphic chip. We evaluate our approach on keyword recognition tasks using the Spiking Heidelberg Digits and Spiking Speech Commands datasets, demonstrating that our algorithm can enhance classification accuracy compared to architectures without delays. Our benchmarking indicates almost no accuracy loss between GPU and Loihi 2 implementations, while classification on Loihi 2 is up to 18x faster and uses 250x less energy than on an NVIDIA Jetson Orin Nano.

cs.NE↗

arXiv2025

FeNN: A RISC-V vector processor for Spiking Neural Network acceleration

Spiking Neural Networks (SNNs) have the potential to drastically reduce the energy requirements of AI systems. However, mainstream accelerators like GPUs and TPUs are designed for the high arithmetic intensity of standard ANNs so are not well-suited to SNN simulation. FPGAs are well-suited to applications with low arithmetic intensity as they have high off-chip memory bandwidth and large amounts of on-chip memory. Here, we present a novel RISC-V-based soft vector processor (FeNN), tailored to simulating SNNs on FPGAs. Unlike most dedicated neuromorphic hardware, FeNN is fully programmable and designed to be integrated with applications running on standard computers from the edge to the cloud. We demonstrate that, by using stochastic rounding and saturation, FeNN can achieve high numerical precision with low hardware utilisation and that a single FeNN core can simulate an SNN classifier faster than both an embedded GPU and the Loihi neuromorphic system.

cs.NE↗

arXiv2025

Constructive community race: full-density spiking neural network model drives neuromorphic computing

The local circuitry of the mammalian brain is a focus of the search for generic computational principles because it is largely conserved across species and modalities. In 2014 a model was proposed representing all neurons and synapses of the stereotypical cortical microcircuit below $1\,\text{mm}^2$ of brain surface. The model reproduces fundamental features of brain activity but its impact remained limited because of its computational demands. For theory and simulation, however, the model was a breakthrough because it removes uncertainties of downscaling, and larger models are less densely connected. This sparked a race in the neuromorphic computing community and the model became a de facto standard benchmark. Within a few years real-time performance was reached and surpassed at significantly reduced energy consumption. We review how the computational challenge was tackled by different simulation technologies and derive guidelines for the next generation of benchmarks and other domains of science.

cs.PF↗

arXiv2025

Eventprop training for efficient neuromorphic applications

Neuromorphic computing can reduce the energy requirements of neural networks and holds the promise to `repatriate' AI workloads back from the cloud to the edge. However, training neural networks on neuromorphic hardware has remained elusive. Here, we instead present a pipeline for training spiking neural networks on GPUs, using the efficient event-driven Eventprop algorithm implemented in mlGeNN, and deploying them on Intel's Loihi 2 neuromorphic chip. Our benchmarking on keyword spotting tasks indicates that there is almost no loss in accuracy between GPU and Loihi 2 implementations and that classifying a sample on Loihi 2 is up to 10X faster and uses 200X less energy than on an NVIDIA Jetson Orin Nano.

cs.NE↗

arXiv2025

Efficient Event-based Delay Learning in Spiking Neural Networks

Spiking Neural Networks (SNNs) compute using sparse communication and are attracting increased attention as a more energy-efficient alternative to traditional Artificial Neural Networks~(ANNs). While standard ANNs are stateless, spiking neurons are stateful and hence intrinsically recurrent, making them well-suited for spatio-temporal tasks. However, the duration of this intrinsic memory is limited by synaptic and membrane time constants. Delays are a powerful additional mechanism and, in this paper, we propose a novel event-based training method for SNNs with delays, grounded in the EventProp formalism which enables the calculation of exact gradients with respect to weights and delays. Our method supports multiple spikes per neuron and, to the best of our knowledge, is the first delay learning algorithm to be applied to recurrent SNNs. We evaluate our method on a simple sequence detection task, as well as the Yin-Yang, Spiking Heidelberg Digits, Spiking Speech Commands and Braille letter reading datasets, demonstrating that our algorithm can optimise delays from suboptimal initial conditions and enhance classification accuracy compared to architectures without delays. We also find that recurrent delays are particularly beneficial in small networks. Finally, we show that our approach uses less than half the memory of the current state-of-the-art delay-learning method and is up to 26x faster.

cs.NE↗

arXiv2024

Learning Delays Through Gradients and Structure: Emergence of Spatiotemporal Patterns in Spiking Neural Networks

We present a Spiking Neural Network (SNN) model that incorporates learnable synaptic delays through two approaches: per-synapse delay learning via Dilated Convolutions with Learnable Spacings (DCLS) and a dynamic pruning strategy that also serves as a form of delay learning. In the latter approach, the network dynamically selects and prunes connections, optimizing the delays in sparse connectivity settings. We evaluate both approaches on the Raw Heidelberg Digits keyword spotting benchmark using Backpropagation Through Time with surrogate gradients. Our analysis of the spatio-temporal structure of synaptic interactions reveals that, after training, excitation and inhibition group together in space and time. Notably, the dynamic pruning approach, which employs DEEP R for connection removal and RigL for reconnection, not only preserves these spatio-temporal patterns but outperforms per-synapse delay learning in sparse networks. Our results demonstrate the potential of combining delay learning with dynamic pruning to develop efficient SNN models for temporal data processing. Moreover, the preservation of spatio-temporal dynamics throughout pruning and rewiring highlights the robustness of these features, providing a solid foundation for future neuromorphic computing applications.

cs.NE↗

arXiv2024

Spyx: A Library for Just-In-Time Compiled Optimization of Spiking Neural Networks

As the role of artificial intelligence becomes increasingly pivotal in modern society, the efficient training and deployment of deep neural networks have emerged as critical areas of focus. Recent advancements in attention-based large neural architectures have spurred the development of AI accelerators, facilitating the training of extensive, multi-billion parameter models. Despite their effectiveness, these powerful networks often incur high execution costs in production environments. Neuromorphic computing, inspired by biological neural processes, offers a promising alternative. By utilizing temporally-sparse computations, Spiking Neural Networks (SNNs) offer to enhance energy efficiency through a reduced and low-power hardware footprint. However, the training of SNNs can be challenging due to their recurrent nature which cannot as easily leverage the massive parallelism of modern AI accelerators. To facilitate the investigation of SNN architectures and dynamics researchers have sought to bridge Python-based deep learning frameworks such as PyTorch or TensorFlow with custom-implemented compute kernels. This paper introduces Spyx, a new and lightweight SNN simulation and optimization library designed in JAX. By pre-staging data in the expansive vRAM of contemporary accelerators and employing extensive JIT compilation, Spyx allows for SNN optimization to be executed as a unified, low-level program on NVIDIA GPUs or Google TPUs. This approach achieves optimal hardware utilization, surpassing the performance of many existing SNN training frameworks while maintaining considerable flexibility.

cs.NE↗

arXiv2024

Learning efficient backprojections across cortical hierarchies in real time

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, which however requires biologically implausible weight transport from feed-forward to feedback paths. We introduce Phaseless Alignment Learning (PAL), a bio-plausible method to learn efficient feedback weights in layered cortical hierarchies. This is achieved by exploiting the noise naturally found in biophysical systems as an additional carrier of information. In our dynamical system, all weights are learned simultaneously with always-on plasticity and using only information locally available to the synapses. Our method is completely phase-free (no forward and backward passes or phased learning) and allows for efficient error propagation across multi-layer cortical hierarchies, while maintaining biologically plausible signal transport and learning. Our method is applicable to a wide class of models and improves on previously known biologically plausible ways of credit assignment: compared to random synaptic feedback, it can solve complex tasks with less neurons and learn more useful latent representations. We demonstrate this on various classification tasks using a cortical microcircuit model with prospective coding.

q-bio.NC↗

arXiv2023

NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems

Neuromorphic computing shows promise for advancing computing efficiency and capabilities of AI applications using brain-inspired principles. However, the neuromorphic research field currently lacks standardized benchmarks, making it difficult to accurately measure technological advancements, compare performance with conventional methods, and identify promising future research directions. Prior neuromorphic computing benchmark efforts have not seen widespread adoption due to a lack of inclusive, actionable, and iterative benchmark design and guidelines. To address these shortcomings, we present NeuroBench: a benchmark framework for neuromorphic computing algorithms and systems. NeuroBench is a collaboratively-designed effort from an open community of researchers across industry and academia, aiming to provide a representative structure for standardizing the evaluation of neuromorphic approaches. The NeuroBench framework introduces a common set of tools and systematic methodology for inclusive benchmark measurement, delivering an objective reference framework for quantifying neuromorphic approaches in both hardware-independent (algorithm track) and hardware-dependent (system track) settings. In this article, we outline tasks and guidelines for benchmarks across multiple application domains, and present initial performance baselines across neuromorphic and conventional approaches for both benchmark tracks. NeuroBench is intended to continually expand its benchmarks and features to foster and track the progress made by the research community.

cs.AI↗

arXiv2022

Loss shaping enhances exact gradient learning with Eventprop in spiking neural networks

Event-based machine learning promises more energy-efficient AI on future neuromorphic hardware. Here, we investigate how the recently discovered Eventprop algorithm for gradient descent on exact gradients in spiking neural networks can be scaled up to challenging keyword recognition benchmarks. We implemented Eventprop in the GPU-enhanced Neural Networks framework and used it for training recurrent spiking neural networks on the Spiking Heidelberg Digits and Spiking Speech Commands datasets. We found that learning depended strongly on the loss function and extended Eventprop to a wider class of loss functions to enable effective training. We then tested a large number of data augmentations and regularisations as well as exploring different network structures; and heterogeneous and trainable timescales. We found that when combined with two specific augmentations, the right regularisation and a delay line input, Eventprop networks with one recurrent layer achieved state-of-the-art performance on Spiking Heidelberg Digits and good accuracy on Spiking Speech Commands. In comparison to a leading surrogate-gradient-based SNN training method, our GeNN Eventprop implementation is 3X faster and uses 4X less memory. This work is a significant step towards a low-power neuromorphic alternative to current machine learning paradigms.

cs.NE↗

arXiv2014

Scalability and Optimization Strategies for GPU Enhanced Neural Networks (GeNN)

Simulation of spiking neural networks has been traditionally done on high-performance supercomputers or large-scale clusters. Utilizing the parallel nature of neural network computation algorithms, GeNN (GPU Enhanced Neural Network) provides a simulation environment that performs on General Purpose NVIDIA GPUs with a code generation based approach. GeNN allows the users to design and simulate neural networks by specifying the populations of neurons at different stages, their synapse connection densities and the model of individual neurons. In this report we describe work on how to scale synaptic weights based on the configuration of the user-defined network to ensure sufficient spiking and subsequent effective learning. We also discuss optimization strategies particular to GPU computing: sparse representation of synapse connections and occupancy based block-size determination.

cs.DC↗

arXiv2013

ICT System Design & Implementation Using Wireless Sensors to Support Elderly In-home Assistance

Around the globe the number of older people in relation to the rest is constantly growing. As a result, medical and care facilities cannot handle the growing number of patients. Therefore, elderly in-home assistance gets more attention an importance. Due to issues regarding memory, physical strength and reduced self-assessment, old people face a lot of challenges in accomplishing their activities of daily living. This thesis is meant to address these problems by analysing the required infrastructure of a home-care facility as well as the arising issues regarding used components, especially wireless sensors. After the analysis, a prototype of a home-care system is designed and implemented. Furthermore, the issue of energy consumption of the used wireless sensor node is addressed by modifying the intelligence of the used sensor. After that, the design and components of the prototype used for the energy consumption analysis is explained, together with the programming structure of the sensor nodes used in this thesis. Thereupon, the results are of the simulations are discussed and compared with the authors' expectations. Finally the overall outcomes of the thesis are analysed and summed up, followed by a short outlook of further possible improvements and developments.

cs.SE↗

arXiv2006

Emergent Properties in Structurally Dynamic Disordered Cellular Networks

We relate structurally dynamic cellular networks, a class of models we developed in fundamental space-time physics, to SDCA, introduced some time ago by Ilachinski and Halpern. We emphasize the crucial property of a non-linear interaction of network geometry with the matter degrees of freedom in order to emulate the supposedly highly erratic and strongly fluctuating space-time structure on the Planck scale. We then embark on a detailed numerical analysis of various large scale characteristics of several classes of models in order to understand what will happen if some sort of macroscopic or continuum limit is performed. Of particular relevance in this context is a notion of network dimension and its behavior in this limit. Furthermore, the possibility of phase transitions is discussed.

cond-mat.stat-mech↗

arXiv2003

Spatial representation of temporal information through spike timing dependent plasticity

We suggest a mechanism based on spike time dependent plasticity (STDP) of synapses to store, retrieve and predict temporal sequences. The mechanism is demonstrated in a model system of simplified integrate-and-fire type neurons densely connected by STDP synapses. All synapses are modified according to the so-called normal STDP rule observed in various real biological synapses. After conditioning through repeated input of a limited number of of temporal sequences the system is able to complete the temporal sequence upon receiving the input of a fraction of them. This is an example of effective unsupervised learning in an biologically realistic system. We investigate the dependence of learning success on entrainment time, system size and presence of noise. Possible applications include learning of motor sequences, recognition and prediction of temporal sensory information in the visual as well as the auditory system and late processing in the olfactory system of insects.

nlin.AO↗

arXiv2001

Phase diagram of the random field Ising model on the Bethe lattice

The phase diagram of the random field Ising model on the Bethe lattice with a symmetric dichotomous random field is closely investigated with respect to the transition between the ferromagnetic and paramagnetic regime. Refining arguments of Bleher, Ruiz and Zagrebnov [J. Stat. Phys. 93, 33 (1998)] an exact upper bound for the existence of a unique paramagnetic phase is found which considerably improves the earlier results. Several numerical estimates of transition lines between a ferromagnetic and a paramagnetic regime are presented. The obtained results do not coincide with a lower bound for the onset of ferromagnetism proposed by Bruinsma [Phys. Rev. B 30, 289 (1984)]. If the latter one proves correct this would hint to a region of coexistence of stable ferromagnetic phases and a stable paramagnetic phase.

cond-mat.dis-nn↗