Papers for

neuromorphic hardware designers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Spiking neural networks reveal mechanisms behind brain turbulence patterns

Spike-to-Field Mechanisms of Turbulence-Like Dynamics in Spatial Spiking Neural Networks

Abstract: Neural avalanches and turbulence-like brain dynamics are usually measured after neural activity has been coarse-grained into continuous fields, leaving open which spike-level mechanisms can generate these macroscopic observables. We build a spatial leaky integrate-and-fire spiking neural network and explicitly transform spikes into activity-density and Hilbert phase fields. A delayed, distance-dependent, passive-dendrite regime reproducibly generates turbulence-like field structure, including high-amplitude phase-defect tracks, structure-function scaling, and power-law-favored continuous-field avalanche tails. Controls show that firing rate, vortex count, and avalanche tail fits are individually insufficient: destroying delayed propagation, dendritic filtering, or spike timing suppresses key field signatures, while random-space nulls can retain many mathematical phase defects but show weaker spatial structure and synaptic-delay transfer. Biologically motivated gates further shape the regime: PV-like perisomatic inhibition clamps phase dynamics, SST-like dendritic inhibition and projection-specific inhibitory facilitation preserve long-lived tracks, and a rate-constrained projection-STP regime expresses a roughly 200-ms episode at 12.25 Hz (full-record mean) across 12 seeds. These results use SNNs as a mechanistic testbed for spike-derived brain turbulence observables and show why phase defects and avalanche-like statistics must be interpreted jointly with spatial scaling and spike-level propagation.

Mon 9 NovMachine Learning
The gist
Scientists created a computer model of brain cells that fire tiny electrical pulses called spikes. They transformed these spikes into patterns that look like turbulent flows seen in the brain. Their model shows that specific delays and special filtering in connections between cells create these complex patterns. The study explains why both individual spike timing and larger-scale activity patterns are important to understand brain turbulence. It also shows how different types of brain cell inhibition affect these patterns.
Open → 2611.12627v1

Method finds simple local learning rules to replace backpropagation

A method to automatically discover symbolic local learning rules

Abstract: We present a general method for discovering symbolic local learning rules that can replace backpropagation, applicable, in principle, to any deep learning architecture and task. The method automatically discovers local loss functions specific to each layer by (1) constructing a dictionary of monomials of local tensor variables, inspired by Penrose diagram notation, (2) regressing over coefficients weighting these monomials to build layerwise polynomial losses whose gradients together minimize a target global loss. We test the method on classification, reconstruction, and self-supervised learning tasks with small multilayer networks and minimal datasets. Across all tasks, the discovered rules induce non-trivial interactions between layers, which lead to significant reductions in the corresponding global losses. Furthermore, the method selects sparse combinations of monomials, finding local rules that are more interpretable than those generated by MLP-based alternatives. The potential implications of our method range from energy-efficient deep learning to the discovery of biologically plausible learning mechanisms.

Mon 9 NovMachine LearningNeural and Evolutionary Computing
The gist
Training deep learning models usually requires a technique called backpropagation, which is complex and can be energy-intensive. This paper shows a way to automatically discover simpler, local rules that each layer in a network can use to learn without needing full backpropagation. The authors demonstrate their method on small networks and various tasks, showing it can effectively reduce overall errors. Their approach also produces simpler rules that are easier to understand compared to some other methods.
Open → 2611.12248v1

Spiking neural networks timing impacts data privacy and accuracy

Characterizing Privacy Leakage in Spiking Neural Networks: A Systematic Analysis of Temporal Dynamics, Stochasticity, Neuronal Dynamics and Learning Mechanisms

Abstract: Spiking neural networks (SNNs) encode information not only in whether neurons fire but also in when they fire, and this temporal dimension shapes what a trained network reveals about its training data. Biologically inspired firing patterns can reduce membership leakage in SNNs without changing the network architecture, which positions temporal dynamics as a design variable for privacy. A change in firing behavior, however, alters stochasticity, spike timing, neuronal response, and the learning problem at once, so harnessing this effect requires identifying which of these properties produces it. This study traces that origin by separating temporal representation, stochasticity, intrinsic neuron dynamics, and learning within a common experimental framework, evaluated under a black-box membership inference attack across image and tabular benchmarks. Varying the temporal representation shows that burst-like firing patterns reduce leakage relative to regular spiking, but at a cost in accuracy. Injecting randomness into the input, spike timing, and spike trains does not reproduce this reduction in leakage, which shows that the reduction arises from how spikes are arranged in time rather than from noise. The privacy benefit further depends on where these firing patterns originate. When neurons generate these patterns through their own adaptive dynamics, leakage falls while accuracy is preserved, so privacy no longer comes at the expense of performance. The learning algorithm then sets the baseline leakage. Under evolutionary training, the attack already performs near chance level, leaving temporal dynamics little room to improve privacy further. Privacy in SNNs is therefore not an inherent property of spikes but a product of how temporal activity is generated, processed, and learned, which offers a principled basis for designing neuromorphic systems that protect sensitive data.

Mon 26 OctNeural and Evolutionary Computing
The gist
Spiking neural networks communicate using the exact timing of their neuron signals, and this timing can affect how much information about their training data leaks out. The authors studied how different firing patterns and randomness in timing impact privacy, finding that burst-like patterns can reduce data leakage but usually lower accuracy. However, when these burst patterns come naturally from the neuron's internal behavior, they can protect privacy without hurting performance. This means privacy in these networks depends more on how their activity is generated and learned than on the spikes themselves.
Open → 2610.36243v1

Learning stability requires frequent and clear feedback signals

On the stability of learning

Abstract: Learning algorithms are usually analyzed under the assumption that informative gradients are continuously available. But this is not always true---learning signals in biological neural networks, for example, may be sparse, local, and only intermittently available at any given synapse. In this work, we show that if gradient information is noisy and only intermittently available, learning may be unstable. In particular, even if average learning dynamics converge to the correct optimum, variance in learning may be asymptotically infinite. We explore this point in a number of analytically tractable settings, including single-layer and multi-layer linear networks, and derive explicit conditions under which learning is stable. These conditions complement, but are conceptually distinct from, existing conditions related to the stability of stochastic gradient descent. Our work demonstrates that unbiased credit assignment is not enough for reliable learning; sufficiently frequent and informative feedback is also required, which yields an additional constraint on models of biologically plausible learning.

Mon 26 OctMachine Learning
The gist
Learning often depends on having useful information available all the time, but in some systems like the brain, this information can be rare and noisy. The authors show that if this learning signal is often missing or noisy, the learning process can become unstable even if it seems to be going in the right direction on average. They analyze simple network models and find conditions that ensure learning stays stable, showing that just correct feedback isn't enough; it must also be frequent and clear. This insight adds new understanding to how learning can be reliable in both artificial and biological systems.
Open → 2610.35856v1

Spiking neural networks learn continuously using focused memory storage

Saliency-Guided Replay for Continual Learning in Deep Spiking Neural Networks

Abstract: Spiking Neural Networks (SNNs) are promising for energy-efficient neuromorphic computing, but they still suffer from catastrophic forgetting when learning tasks sequentially. This work investigates the integration of Experience Packing and Replay (EPR) as a memory-efficient continual learning strategy for deep SNNs under low-latency constraints. The proposed framework combines Batch Normalization Through Time stabilized VGG9 SNNs with Spike Activation Maps (SAM), which provide forward-only explanations based on spike activity. These explanations are temporally aggregated into spatial attention maps and used to select the most informative image patches for replay, instead of storing full images. Experiments on Split CIFAR10 and Split CIFAR100 show that SAM-guided EPR improves the accuracy-memory trade-off under tight memory budgets, and remains competitive while requiring substantially less storage.

Tue 13 OctMachine LearningArtificial IntelligenceComputer Vision and Pattern Recognition
The gist
Deep spiking neural networks are a type of artificial brain model that can learn, but they often forget old knowledge when learning new tasks one after another. The authors suggest a way to help these networks remember by saving only the important parts of images they saw before, rather than whole pictures. They use a special technique that figures out which image areas the network pays attention to when making decisions and store just those parts. This approach allows the networks to learn multiple tasks in sequence while using less memory without losing accuracy.
Open → 2610.17998v1

Spiking transformer attention works like physical two-level systems

Softmax-Free Attention in Spiking Transformers as the Zero-Temperature Limit of Two-Level Systems

Abstract: Spiking Transformers achieve energy efficiency by discarding softmax normalization in favor of thresholded, binary attention. However, this removal breaks the thermodynamic framework used to analyze attention networks, as the normalized measure and partition function cease to exist. We restore this theoretical foundation by proving that softmax-free spiking attention operates exactly as the zero-temperature limit of a product of independent two-level systems. This correspondence places spiking attention strictly in the frozen ordered phase of the thermodynamic phase diagram for all inputs. Consequently, the entropic cost of organizing attention collapses, replaced by a Landauer-type physical floor governed by action-potential generation. Furthermore, this ordered-phase pinning mathematically explains the optimization difficulty caused by vanishing surrogate gradients. We validate this theory with forward-relaxation experiments, placing both standard and neuromorphic attention mechanisms on a unified thermodynamic axis.

Sun 11 OctMachine Learning
The gist
Spiking Transformers save energy by skipping softmax normalization used in regular attention models, but this breaks existing ways to understand how attention works using thermodynamics. The authors show that softmax-free spiking attention behaves like a physical system cooled to absolute zero, which explains why optimization can be hard and why energy use hits a fundamental limit. They test their theory and place both standard and spiking attention on the same thermodynamic scale to unify understanding.
Open → 2610.15968v1

Proteinoid networks formalized for information processing and intelligence

Formalisation of information processing and intelligence in proteinoid networks

Abstract: Proteinoid microspheres are electrically active assemblies of thermally polymerised amino acids that exhibit spontaneous oscillations, spike-like events, stimulus-dependent responses, adaptation and collective dynamics. We formulate these observations as an applied-mathematical problem and develop a unified dynamical framework for information processing in proteinoid networks. Individual microspheres are represented by nonlinear excitable or oscillatory systems, whereas interactions are described by weighted adaptive graphs and, in the spatial limit, reaction--diffusion dynamics. The framework combines signal propagation, attenuation, fading memory, adaptive coupling, synchronisation, information transfer, reservoir readout, robustness and energetic constraints. We define a task-relative proteinoid intelligence functional from normalised measures of stimulus information, memory, adaptation, directed information transfer, task performance and robustness, penalised by energetic and structural costs. Analytical results establish a joint-response information bound, an upper bound on linear memory for stable linear networks, and existence of an optimal admissible coupling matrix under compact constraints. Dimensionless groups identify the relative time scales and coupling regimes governing the problem in nonlinear and adaptive network dynamics.

Fri 9 OctEmerging Technologies
The gist
Scientists studied tiny spheres made from chains of amino acids, called proteinoid microspheres, which can send electrical signals and respond to their environment in ways that look a bit like simple intelligence. They created a math-based framework to explain how these spheres process information, work together, and adapt over time. This framework captures how signals move, fade, and strengthen, and even measures how well these spheres can remember and respond to tasks efficiently. They also found limits on how much information can be processed and how memory works in these networks, which helps understand their potential smart behavior. This work combines ideas from biology, math, and computer science to better grasp how simple networks might perform information tasks.
Open → 2610.13545v1

Voltage-controlled neurons cut computing energy with new spintronics design

A Voltage-controlled MTJ-CMOS Neuron Emulating Tunable Izhikevich-Inspired Dynamics

Abstract: Biological neurons exhibit diverse firing dynamics that enable adaptive and stimulus-dependent signalling, yet reproducing these dynamics in hardware has remained an enduring challenge. In this work, we present an Izhikevich- inspired reconfigurable neuron that co-designs voltage-controlled magnetic tunnel junction (V-MTJ) dynamics with CMOS circuitry. The proposed architecture combines V-MTJ excitability dynamics, enabled by a tunable energy landscape, with CMOS recovery dynamics to generate five distinct neuronal firing pat- terns with different spiking, bursting and response characteristics. Our results, based on measured V-MTJ characteristics and circuit simulations using com- mercial GlobalFoundries 22-nm FD-SOI CMOS technology, show an average energy consumption of 145.44 fJ per spike. Algorithmic simulations further show that these firing dynamics reduce inference spike activity by up to 88.6% while maintaining baseline classification accuracy. These results highlight the potential of V-MTJ/CMOS reconfigurable neurons to reduce computational activity and enable compact, energy-efficient brain-inspired computing systems.

Fri 25 SeptEmerging TechnologiesHardware ArchitectureNeural and Evolutionary Computing
The gist
Building computers that work like brains is hard because brain cells fire in many different ways. The authors made a new neuron design combining special magnetic parts with standard computer chips to mimic five different firing patterns. They showed this design uses very little energy per signal and can reduce the amount of work needed for certain tasks while keeping accuracy high. This could help make brain-inspired computers more efficient and compact.
Open → 2609.32031v1

Spiking neural networks reduce communication and improve accuracy with predictive coding

Predictive Suppression Layers for Communication-Efficient Spiking Neural Networks

Abstract: Feedforward Spiking Neural Networks (SNNs) typically propagate every generated spike indiscriminately, disregarding whether the information is redundant from an information-theoretic perspective. This lack of selectivity induces high redundancy in inter-layer communication, creating an expensive overhead, e.g., in scenarios involving many-core neuromorphic hardware or communication-dominated Internet-of-Things (IoT) where features are transmitted wirelessly. To address this challenge, we trade localized processing for leaner network channels by introducing a minimal predictive coding framework for SNNs. We propose two layer variants sharing a predictor block: error units, which transmit signed spiking residuals, and predictive suppression, which uses residual magnitude to dynamically gate and forward only unpredictable, "surprising" activity. Evaluated on the N-MNIST and Spiking Heidelberg Digits (SHD) datasets using diagnostic metrics that decouple local processing from cross-layer communication, our new predictive coding layers achieve significant communication savings. Numerical results reveal a three-fold reduction in communicated activity, while increasing the task accuracy for both datasets. The latter finding is notable, and suggests that predictive coding layers not only minimize communication overhead, but also produce output feature vectors with a higher representation power.

Fri 18 SeptNeural and Evolutionary ComputingMachine Learning
The gist
Spiking neural networks send signals called spikes to process information, but they often send too many redundant spikes that waste resources. The authors propose a way for these networks to predict which spikes are important to send and suppress the rest, much like only sharing surprising news. This method cuts the communication needed by about three times while actually making the network better at its tasks. This approach helps in settings where communicating data is costly or slow, like in low-power devices or networks with many processing units.
Open → 2609.21583v1