arXiv subjects

Dominik Dold

Publications and source records attributed to Dominik Dold.

At least 19 recordsLinked to original sources

arXiv2026

Equivalence of approximation by networks of single- and multi-spike neurons

In a spiking neural network, is it enough for each neuron to spike at most once? In recent work, approximation bounds for spiking neural networks have been derived, quantifying how well they can fit target functions. However, these results are only valid for neurons that spike at most once, which is commonly thought to be a strong limitation. Here, we show that the opposite is true for a large class of spiking neuron models, including the commonly used leaky integrate-and-fire model with subtractive reset: for every approximation bound that is valid for a set of multi-spike neural networks, there is an equivalent set of single-spike neural networks with only linearly more neurons (in the maximum number of spikes) for which the bound holds. The same is true for the reverse direction too, showing that regarding their approximation capabilities in general machine learning tasks, single-spike and multi-spike neural networks are equivalent. Consequently, many approximation results in the literature for single-spike neural networks also hold for the multi-spike case.

cs.NE↗

arXiv2025

Reconfiguration of pivoting cube ensembles under local sensing constraints using geometric deep learning

We demonstrate that local sensing is sufficient for effective global reconfiguration of homogeneous pivoting cube modular robots in two dimensions. While cube selection (i.e., which cube executes a movement) is assumed to be globally coordinated, each cube in the ensemble is controlled by a neural network that only gains information from other cubes in its local neighbourhood, trained using reinforcement learning. Furthermore, we study the effect of including grid symmetries of the cube ensemble (rotation and mirroring) in the neural network architecture. We find that even the most localised versions succeed in reconfiguring to the target shape, although reconfiguration happens faster the more information about the whole ensemble is available to individual cubes. Near-optimal reconfiguration is achieved with only nearest neighbour interactions by using multiple information passing between cubes, allowing them to accumulate more global information about the ensemble. Compared to standard neural network architectures, including grid symmetries provides only minor benefits during training, but allows for reduced model sizes. The presented approach is transferable to other space-relevant systems with different action spaces, such as sliding cube modular robots and CubeSat swarms.

cs.NE↗

arXiv2025

Memristor-Based Neural Network Accelerators for Space Applications: Enhancing Performance with Temporal Averaging and SIRENs

Memristors are an emerging technology that enables artificial intelligence (AI) accelerators with high energy efficiency and radiation robustness -- properties that are vital for the deployment of AI on-board spacecraft. However, space applications require reliable and precise computations, while memristive devices suffer from non-idealities, such as device variability, conductance drifts, and device faults. Thus, porting neural networks (NNs) to memristive devices often faces the challenge of severe performance degradation. In this work, we show in simulations that memristor-based NNs achieve competitive performance levels on on-board tasks, such as navigation \& control and geodesy of asteroids. Through bit-slicing, temporal averaging of NN layers, and periodic activation functions, we improve initial results from around $0.07$ to $0.01$ and $0.3$ to $0.007$ for both tasks using RRAM devices, coming close to state-of-the-art levels ($0.003-0.005$ and $0.003$, respectively). Our results demonstrate the potential of memristors for on-board space applications, and we are convinced that future technology and NN improvements will further close the performance gap to fully unlock the benefits of memristors.

eess.SY↗

arXiv2025

Guidance and Control Neural Network Acceleration using Memristors

In recent years, the space community has been exploring the possibilities of Artificial Intelligence (AI), specifically Artificial Neural Networks (ANNs), for a variety of on board applications. However, this development is limited by the restricted energy budget of smallsats and cubesats as well as radiation concerns plaguing modern chips. This necessitates research into neural network accelerators capable of meeting these requirements whilst satisfying the compute and performance needs of the application. This paper explores the use of Phase-Change Memory (PCM) and Resistive Random-Access Memory (RRAM) memristors for on-board in-memory computing AI acceleration in space applications. A guidance and control neural network (G\&CNET) accelerated using memristors is simulated in a variety of scenarios and with both device types to evaluate the performance of memristor-based accelerators, considering device non-idealities such as noise and conductance drift. We show that the memristive accelerator is able to learn the expert actions, though challenges remain with the impact of noise on accuracy. We also show that re-training after degradation is able to restore performance to nominal levels. This study provides a foundation for future research into memristor-based AI accelerators for space, highlighting their potential and the need for further investigation.

cs.AR↗

arXiv2025

Energy efficiency analysis of Spiking Neural Networks for space applications

While the exponential growth of the space sector and new operative concepts ask for higher spacecraft autonomy, the development of AI-assisted space systems was so far hindered by the low availability of power and energy typical of space applications. In this context, Spiking Neural Networks (SNN) are highly attractive due to their theoretically superior energy efficiency due to their inherently sparse activity induced by neurons communicating by means of binary spikes. Nevertheless, the ability of SNN to reach such efficiency on real world tasks is still to be demonstrated in practice. To evaluate the feasibility of utilizing SNN onboard spacecraft, this work presents a numerical analysis and comparison of different SNN techniques applied to scene classification for the EuroSAT dataset. Such tasks are of primary importance for space applications and constitute a valuable test case given the abundance of competitive methods available to establish a benchmark. Particular emphasis is placed on models based on temporal coding, where crucial information is encoded in the timing of neuron spikes. These models promise even greater efficiency of resulting networks, as they maximize the sparsity properties inherent in SNN. A reliable metric capable of comparing different architectures in a hardware-agnostic way is developed to establish a clear theoretical dependence between architecture parameters and the energy consumption that can be expected onboard the spacecraft. The potential of this novel method and his flexibility to describe specific hardware platforms is demonstrated by its application to predicting the energy consumption of a BrainChip Akida AKD1000 neuromorphic processor.

cs.NE↗

arXiv2025

Causal pieces: analysing and improving spiking neural networks piece by piece

We introduce a novel concept for spiking neural networks (SNNs) derived from the idea of "linear pieces" used to analyse the expressiveness and trainability of artificial neural networks (ANNs). We prove that the input domain of SNNs decomposes into distinct causal regions where its output spike times are locally Lipschitz continuous with respect to the input spike times and network parameters. The number of such regions - which we call "causal pieces" - is a measure of the approximation capabilities of SNNs. In particular, we demonstrate in simulation that parameter initialisations which yield a high number of causal pieces on the training set strongly correlate with SNN training success. Moreover, we find that feedforward SNNs with purely positive weights exhibit a surprisingly high number of causal pieces, allowing them to achieve competitive performance levels on benchmark tasks. We believe that causal pieces are not only a powerful and principled tool for improving SNNs, but might also open up new ways of comparing SNNs and ANNs in the future.

cs.NE↗

arXiv2024

Continuous Design and Reprogramming of Totimorphic Structures for Space Applications

Recently, a class of mechanical lattices with reconfigurable, zero-stiffness structures has been proposed, called Totimorphic lattices. In this work, we introduce a computational framework that enables continuous reprogramming of a Totimorphic lattice's effective properties, such as mechanical and optical behaviour, through geometric changes alone, demonstrated using computer simulations. Our approach is differentiable and guarantees valid Totimorphic configurations throughout the optimisation process, providing not only target states with desired properties but also continuous trajectories in configuration space that connect them. This enables reprogrammable structures in which actuators are controlled via automatic differentiation on an objective-dependent cost function, continuously adapting the lattice to achieve a given goal. We focus on deep space applications, where harsh and resource-constrained environments demand solutions that combine flexibility, efficiency, and autonomy. As proof of concept, we present two scenarios: a reprogrammable disordered lattice material and a space telescope mirror with adjustable focal length. The introduced framework is adaptable to a wide range of Totimorphic designs and objectives, providing a lightweight model for endowing physical systems with autonomous self-configuration and self-repair capabilities.

astro-ph.IM↗

arXiv2024

Stable Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders

We study the learning problem associated with spiking neural networks. Specifically, we focus on spiking neural networks composed of simple spiking neurons having only positive synaptic weights, equipped with an affine encoder and decoder; we refer to these as affine spiking neural networks. These neural networks are shown to depend continuously on their parameters, which facilitates classical covering number-based generalization statements and supports stable gradient-based training. We demonstrate that the positivity of the weights enables a wide range of expressivity results, including rate-optimal approximation of smooth functions and dimension-independent approximation of Barron regular functions. In particular, we show in theory and simulations that affine spiking neural networks are capable of approximating shallow ReLU neural networks. Furthermore, we apply these affine spiking neural networks to standard machine learning benchmarks and reach competitive results. Finally, we observe that from a generalization perspective, contrary to feedforward neural networks or previous results for general spiking neural networks, the depth has little to no adverse effect on the generalization capabilities.

cs.NE↗

arXiv2024

Scalable Network Emulation on Analog Neuromorphic Hardware

We present a novel software feature for the BrainScaleS-2 accelerated neuromorphic platform that facilitates the partitioned emulation of large-scale spiking neural networks. This approach is well suited for deep spiking neural networks and allows for sequential model emulation on undersized neuromorphic resources if the largest recurrent subnetwork and the required neuron fan-in fit on the substrate. The ability to emulate and train networks larger than the substrate provides a pathway for accurate performance evaluation in planned or scaled systems, ultimately advancing the development and understanding of large-scale models and neuromorphic computing architectures. We demonstrate the training of two deep spiking neural network models -- using the MNIST and EuroSAT datasets -- that exceed the physical size constraints of a single-chip BrainScaleS-2 system.

cs.NE↗

arXiv2023

Totimorphic structures for space application

We propose to use a recently introduced Totimorphic metamaterial for constructing morphable space structures. As a first step to investigate the feasibility of this concept, we present a method for morphing such structures autonomously between different shapes using physically plausible actuations, guaranteeing that the material traverses through valid configurations only while morphing. With this work, we aim to lay a foundation for exploring a promising and novel class of multi-functional, reconfigurable space structures.

cond-mat.mtrl-sci↗

arXiv2023

Differentiable graph-structured models for inverse design of lattice materials

Architected materials possessing physico-chemical properties adaptable to disparate environmental conditions embody a disruptive new domain of materials science. Fueled by advances in digital design and fabrication, materials shaped into lattice topologies enable a degree of property customization not afforded to bulk materials. A promising venue for inspiration toward their design is in the irregular micro-architectures of nature. However, the immense design variability unlocked by such irregularity is challenging to probe analytically. Here, we propose a new computational approach using graph-based representation for regular and irregular lattice materials. Our method uses differentiable message passing algorithms to calculate mechanical properties, therefore allowing automatic differentiation with surrogate derivatives to adjust both geometric structure and local attributes of individual lattice elements to achieve inversely designed materials with desired properties. We further introduce a graph neural network surrogate model for structural analysis at scale. The methodology is generalizable to any system representable as heterogeneous graphs.

cond-mat.mtrl-sci↗

arXiv2022

Detection, Explanation and Filtering of Cyber Attacks Combining Symbolic and Sub-Symbolic Methods

Machine learning (ML) on graph-structured data has recently received deepened interest in the context of intrusion detection in the cybersecurity domain. Due to the increasing amounts of data generated by monitoring tools as well as more and more sophisticated attacks, these ML methods are gaining traction. Knowledge graphs and their corresponding learning techniques such as Graph Neural Networks (GNNs) with their ability to seamlessly integrate data from multiple domains using human-understandable vocabularies, are finding application in the cybersecurity domain. However, similar to other connectionist models, GNNs are lacking transparency in their decision making. This is especially important as there tend to be a high number of false positive alerts in the cybersecurity domain, such that triage needs to be done by domain experts, requiring a lot of man power. Therefore, we are addressing Explainable AI (XAI) for GNNs to enhance trust management by exploring combining symbolic and sub-symbolic methods in the area of cybersecurity that incorporate domain knowledge. We experimented with this approach by generating explanations in an industrial demonstrator system. The proposed method is shown to produce intuitive explanations for alerts for a diverse range of scenarios. Not only do the explanations provide deeper insights into the alerts, but they also lead to a reduction of false positive alerts by 66% and by 93% when including the fidelity metric.

cs.CR↗

arXiv2022

Neuromorphic Computing and Sensing in Space

The term ``neuromorphic'' refers to systems that are closely resembling the architecture and/or the dynamics of biological neural networks. Typical examples are novel computer chips designed to mimic the architecture of a biological brain, or sensors that get inspiration from, e.g., the visual or olfactory systems in insects and mammals to acquire information about the environment. This approach is not without ambition as it promises to enable engineered devices able to reproduce the level of performance observed in biological organisms -- the main immediate advantage being the efficient use of scarce resources, which translates into low power requirements. The emphasis on low power and energy efficiency of neuromorphic devices is a perfect match for space applications. Spacecraft -- especially miniaturized ones -- have strict energy constraints as they need to operate in an environment which is scarce with resources and extremely hostile. In this work we present an overview of early attempts made to study a neuromorphic approach in a space context at the European Space Agency's (ESA) Advanced Concepts Team (ACT).

cs.NE↗

arXiv2022

Selected Trends in Artificial Intelligence for Space Applications

The development and adoption of artificial intelligence (AI) technologies in space applications is growing quickly as the consensus increases on the potential benefits introduced. As more and more aerospace engineers are becoming aware of new trends in AI, traditional approaches are revisited to consider the applications of emerging AI technologies. Already at the time of writing, the scope of AI-related activities across academia, the aerospace industry and space agencies is so wide that an in-depth review would not fit in these pages. In this chapter we focus instead on two main emerging trends we believe capture the most relevant and exciting activities in the field: differentiable intelligence and on-board machine learning. Differentiable intelligence, in a nutshell, refers to works making extensive use of automatic differentiation frameworks to learn the parameters of machine learning or related models. Onboard machine learning considers the problem of moving inference, as well as learning, onboard. Within these fields, we discuss a few selected projects originating from the European Space Agency's (ESA) Advanced Concepts Team (ACT), giving priority to advanced topics going beyond the transposition of established AI techniques and practices to the space domain.

cs.LG↗

arXiv2022

Neuro-symbolic computing with spiking neural networks

Knowledge graphs are an expressive and widely used data structure due to their ability to integrate data from different domains in a sensible and machine-readable way. Thus, they can be used to model a variety of systems such as molecules and social networks. However, it still remains an open question how symbolic reasoning could be realized in spiking systems and, therefore, how spiking neural networks could be applied to such graph data. Here, we extend previous work on spike-based graph algorithms by demonstrating how symbolic and multi-relational information can be encoded using spiking neurons, allowing reasoning over symbolic structures like knowledge graphs with spiking neural networks. The introduced framework is enabled by combining the graph embedding paradigm and the recent progress in training spiking neural networks using error backpropagation. The presented methods are applicable to a variety of spiking neuron models and can be trained end-to-end in combination with other differentiable network architectures, which we demonstrate by implementing a spiking relational graph neural network.

cs.NE↗

arXiv2022

Relational representation learning with spike trains

Relational representation learning has lately received an increase in interest due to its flexibility in modeling a variety of systems like interacting particles, materials and industrial projects for, e.g., the design of spacecraft. A prominent method for dealing with relational data are knowledge graph embedding algorithms, where entities and relations of a knowledge graph are mapped to a low-dimensional vector space while preserving its semantic structure. Recently, a graph embedding method has been proposed that maps graph elements to the temporal domain of spiking neural networks. However, it relies on encoding graph elements through populations of neurons that only spike once. Here, we present a model that allows us to learn spike train-based embeddings of knowledge graphs, requiring only one neuron per graph element by fully utilizing the temporal domain of spike patterns. This coding scheme can be implemented with arbitrary spiking neuron models as long as gradients with respect to spike times can be calculated, which we demonstrate for the integrate-and-fire neuron model. In general, the presented results show how relational knowledge can be integrated into spike-based systems, opening up the possibility of merging event-based computing and relational data to build powerful and energy efficient artificial intelligence applications and reasoning systems.

cs.NE↗

arXiv2022

Evaluating the feasibility of interpretable machine learning for globular cluster detection

Extragalactic globular clusters (GCs) are important tracers of galaxy formation and evolution. Obtaining GC catalogues from photometric data involves several steps which will likely become too time-consuming to perform on the large data volumes that are expected from upcoming wide-field imaging projects such as Euclid. In this work, we explore the feasibility of various machine learning (ML) methods to aid the search for GCs. We use archival Hubble Space Telescope data in the F475W and F850LP bands of 141 early-type galaxies in the Fornax and Virgo galaxy clusters. Using existing GC catalogues to label the data, we obtain an extensive data set of 84929 sources containing 18556 GCs and we train several ML methods both on image and tabular data containing physically relevant features extracted from the images. We find that our evaluated ML models are capable of producing catalogues of similar quality as the existing ones. The best performing methods, ensemble-based models like random forests and convolutional neural networks, recover ~ 90-94 % of GCs while producing an acceptable amount of false detections (~ 6-8 %) - with some falsely detected sources being identifiable as GCs that have not been labelled as such in the used catalogues. In the magnitude range 22 < m4_g < 24.5 mag, 98 - 99 % of GCs are recovered. We even find such high performance levels when training on Virgo and evaluating on Fornax data (and vice versa), illustrating that the models are transferable to environments with different conditions such as different distances than in the used training data. Additionally, we demonstrate how interpretable methods can be used to better understand model predictions, recovering that magnitudes, colours, and sizes are important for identifying GCs. These are encouraging results, indicating that similar methods can be applied for creating GC catalogues for a large number of galaxies.

astro-ph.GA↗

arXiv2021

An energy-based model for neuro-symbolic reasoning on knowledge graphs

Machine learning on graph-structured data has recently become a major topic in industry and research, finding many exciting applications such as recommender systems and automated theorem proving. We propose an energy-based graph embedding algorithm to characterize industrial automation systems, integrating knowledge from different domains like industrial automation, communications and cybersecurity. By combining knowledge from multiple domains, the learned model is capable of making context-aware predictions regarding novel system events and can be used to evaluate the severity of anomalies that might be indicative of, e.g., cybersecurity breaches. The presented model is mappable to a biologically-inspired neural architecture, serving as a first bridge between graph embedding methods and neuromorphic computing - uncovering a promising edge application for this upcoming technology.

cs.LG↗