arXiv subjects

Balázs Mészáros

Publications and source records attributed to Balázs Mészáros.

6 recordsLinked to original sources

arXiv2026

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

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

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↗

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↗

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↗

arXiv2022

Structural Extensions of Basis Pursuit: Guarantees on Adversarial Robustness

While deep neural networks are sensitive to adversarial noise, sparse coding using the Basis Pursuit (BP) method is robust against such attacks, including its multi-layer extensions. We prove that the stability theorem of BP holds upon the following generalizations: (i) the regularization procedure can be separated into disjoint groups with different weights, (ii) neurons or full layers may form groups, and (iii) the regularizer takes various generalized forms of the $\ell_1$ norm. This result provides the proof for the architectural generalizations of Cazenavette et al. (2021), including (iv) an approximation of the complete architecture as a shallow sparse coding network. Due to this approximation, we settled to experimenting with shallow networks and studied their robustness against the Iterative Fast Gradient Sign Method on a synthetic dataset and MNIST. We introduce classification based on the $\ell_2$ norms of the groups and show numerically that it can be accurate and offers considerable speedups. In this family, linear transformer shows the best performance. Based on the theoretical results and the numerical simulations, we highlight numerical matters that may improve performance further.

cs.LG↗