Tootfinder

Canonical Quantization of a Memristive Leaky Integrate-and-Fire Neuron Circuit
Dean Brand, Domenica Dibenedetto, Francesco Petruccione
https://arxiv.org/abs/2506.21363

Canonical Quantization of a Memristive Leaky Integrate-and-Fire Neuron Circuit
We present a theoretical framework for a quantized memristive Leaky Integrate-and-Fire (LIF) neuron, uniting principles from neuromorphic engineering and open quantum systems. Starting from a classical memristive LIF circuit, we apply canonical quantization techniques to derive a quantum model grounded in circuit quantum electrodynamics. Numerical simulations demonstrate key dynamical features of the quantized memristor and LIF neuron in the weak-coupling and adiabatic regime, including memory …

This https://arxiv.org/abs/2306.11965 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Symmetry's Edge in Cortical Dynamics: Multiscale Dynamics of Ensemble Excitation and Inhibition
Creating a quantitative theory for the cortex presents challenges and raises questions. What are the significant scales--micro, meso, or macroscopic? What are the interactions--pairwise, higher order, or mean-field? And what control parameters are relevant--noisy, dissipative, or emergent? We suggest an approach inspired by advances in understanding matter. This involves identifying invariances in neuron ensemble dynamics, searching for order parameters connecting key degrees of freedom and d…

TopK Language Models
Ryosuke Takahashi, Tatsuro Inaba, Kentaro Inui, Benjamin Heinzerling
https://arxiv.org/abs/2506.21468 https://arxiv.org/pdf/2506.21468 https://arxiv.org/html/2506.21468
arXiv:2506.21468v1 Announce Type: new
Abstract: Sparse autoencoders (SAEs) have become an important tool for analyzing and interpreting the activation space of transformer-based language models (LMs). However, SAEs suffer several shortcomings that diminish their utility and internal validity. Since SAEs are trained post-hoc, it is unclear if the failure to discover a particular concept is a failure on the SAE's side or due to the underlying LM not representing this concept. This problem is exacerbated by training conditions and architecture choices affecting which features an SAE learns. When tracing how LMs learn concepts during training, the lack of feature stability also makes it difficult to compare SAEs features across different checkpoints. To address these limitations, we introduce a modification to the transformer architecture that incorporates a TopK activation function at chosen layers, making the model's hidden states equivalent to the latent features of a TopK SAE. This approach eliminates the need for post-hoc training while providing interpretability comparable to SAEs. The resulting TopK LMs offer a favorable trade-off between model size, computational efficiency, and interpretability. Despite this simple architectural change, TopK LMs maintain their original capabilities while providing robust interpretability benefits. Our experiments demonstrate that the sparse representations learned by TopK LMs enable successful steering through targeted neuron interventions and facilitate detailed analysis of neuron formation processes across checkpoints and layers. These features make TopK LMs stable and reliable tools for understanding how language models learn and represent concepts, which we believe will significantly advance future research on model interpretability and controllability.
toXiv_bot_toot

Prediction: interest in electrode-based BCIs will wane (aside from niches), as non-implantable ("non-invasive") phased array focused ultrasound will take over for both brain stimulation and measuring brain activity https://www.cell.com/neuron/fulltext/S0896-6273(20)…

Causes in neuron diagrams, and testing causal reasoning in Large Language Models. A glimpse of the future of philosophy?
Louis Vervoort, Vitaly Nikolaev
https://arxiv.org/abs/2506.14239

Causes in neuron diagrams, and testing causal reasoning in Large Language Models. A glimpse of the future of philosophy?
We propose a test for abstract causal reasoning in AI, based on scholarship in the philosophy of causation, in particular on the neuron diagrams popularized by D. Lewis. We illustrate the test on advanced Large Language Models (ChatGPT, DeepSeek and Gemini). Remarkably, these chatbots are already capable of correctly identifying causes in cases that are hotly debated in the literature. In order to assess the results of these LLMs and future dedicated AI, we propose a definition of cause in neur…

fly_larva: Drosophila larva brain (2023)
A complete synaptic map of the brain connectome of the larva of the fruit fly Drosophila melanogaster. Nodes are neurons, and edges are synaptic connections, traced individually from brain image sections using three-dimensional electron microscopy–based reconstruction. Node metadata include the neuron hempisphere, hemispherical homologue, cell type, annotations, and inferred cluster. Edge metadata include the type of interaction (`'aa'`,…

Energy-Efficient Digital Design: A Comparative Study of Event-Driven and Clock-Driven Spiking Neurons
Filippo Marostica, Alessio Carpegna, Alessandro Savino, Stefano Di Carlo
https://arxiv.org/abs/2506.13268

Energy-Efficient Digital Design: A Comparative Study of Event-Driven and Clock-Driven Spiking Neurons
This paper presents a comprehensive evaluation of Spiking Neural Network (SNN) neuron models for hardware acceleration by comparing event driven and clock-driven implementations. We begin our investigation in software, rapidly prototyping and testing various SNN models based on different variants of the Leaky Integrate and Fire (LIF) neuron across multiple datasets. This phase enables controlled performance assessment and informs design refinement. Our subsequent hardware phase, implemented on …

Identifying multi-compartment Hodgkin-Huxley models with high-density extracellular voltage recordings
Ian Christopher Tanoh, Michael Deistler, Jakob H. Macke, Scott W. Linderman
https://arxiv.org/abs/2506.20233

Identifying multi-compartment Hodgkin-Huxley models with high-density extracellular voltage recordings
Multi-compartment Hodgkin-Huxley models are biophysical models of how electrical signals propagate throughout a neuron, and they form the basis of our knowledge of neural computation at the cellular level. However, these models have many free parameters that must be estimated for each cell, and existing fitting methods rely on intracellular voltage measurements that are highly challenging to obtain in vivo. Recent advances in neural recording technology with high-density probes and arrays enabl…

Steering Conceptual Bias via Transformer Latent-Subspace Activation
Vansh Sharma, Venkat Raman
https://arxiv.org/abs/2506.18887 https://

Steering Conceptual Bias via Transformer Latent-Subspace Activation
This work examines whether activating latent subspaces in language models (LLMs) can steer scientific code generation toward a specific programming language. Five causal LLMs were first evaluated on scientific coding prompts to quantify their baseline bias among four programming languages. A static neuron-attribution method, perturbing the highest activated MLP weight for a C++ or CPP token, proved brittle and exhibited limited generalization across prompt styles and model scales. To address th…

A Novel Discrete Memristor-Coupled Heterogeneous Dual-Neuron Model and Its Application in Multi-Scenario Image Encryption
Yi Zou, Mengjiao Wang, Xinan Zhang, Herbert Ho-Ching Iu
https://arxiv.org/abs/2505.24294

A Novel Discrete Memristor-Coupled Heterogeneous Dual-Neuron Model and Its Application in Multi-Scenario Image Encryption
Simulating brain functions using neural networks is an important area of research. Recently, discrete memristor-coupled neurons have attracted significant attention, as memristors effectively mimic synaptic behavior, which is essential for learning and memory. This highlights the biological relevance of such models. This study introduces a discrete memristive heterogeneous dual-neuron network (MHDNN). The stability of the MHDNN is analyzed with respect to initial conditions and a range of neuro…

SECNEURON: Reliable and Flexible Abuse Control in Local LLMs via Hybrid Neuron Encryption
Zhiqiang Wang, Haohua Du, Junyang Wang, Haifeng Sun, Kaiwen Guo, Haikuo Yu, Chao Liu, Xiang-Yang Li
https://arxiv.org/abs/2506.05242

SECNEURON: Reliable and Flexible Abuse Control in Local LLMs via Hybrid Neuron Encryption
Large language models (LLMs) with diverse capabilities are increasingly being deployed in local environments, presenting significant security and controllability challenges. These locally deployed LLMs operate outside the direct control of developers, rendering them more susceptible to abuse. Existing mitigation techniques mainly designed for cloud-based LLM services are frequently circumvented or ineffective in deployer-controlled environments. We propose SECNEURON, the first framework that se…

This https://arxiv.org/abs/2506.00691 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Optimizing Sensory Neurons: Nonlinear Attention Mechanisms for Accelerated Convergence in Permutation-Invariant Neural Networks for Reinforcement Learning
Training reinforcement learning (RL) agents often requires significant computational resources and extended training times. To address this, we build upon the foundation laid by Google Brain's Sensory Neuron, which introduced a novel neural architecture for reinforcement learning tasks that maintained permutation in-variance in the sensory neuron system. While the baseline model demonstrated significant performance improvements over traditional approaches, we identified opportunities to enhance…

Impact of Hill coefficient and time delay on a perceptual decision-making model
Bart{\l}omiej Morawski, Anna Czartoszewska
https://arxiv.org/abs/2506.19853

Impact of Hill coefficient and time delay on a perceptual decision-making model
In this paper, a neural mass perceptual decision making model introduced by Piskała et al. is analyzed. The model describes activity of two neuron populations influenced by each other and external inputs. The groups' activities correspond to the process of making a perceptual binary decision. Existing results are generalized by investigating the impact of both a delay in self-inhibition and a generic Hill coefficient on solutions to the system of differential equations. Several versions of the…

This https://arxiv.org/abs/2409.09268 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Spintronic Neuron Using a Magnetic Tunnel Junction for Low-Power Neuromorphic Computing
This paper proposes a novel spiking artificial neuron design based on a combined spin valve/magnetic tunnel junction (SV/MTJ). Traditional hardware used in artificial intelligence and machine learning faces significant challenges related to high power consumption and scalability. To address these challenges, spintronic neurons, which can mimic biologically inspired neural behaviors, offer a promising solution. We present a model of an SV/MTJ-based neuron which uses technologies that have been s…

A Hybrid Artificial Intelligence Method for Estimating Flicker in Power Systems
Javad Enayati, Pedram Asef, Alexandre Benoit
https://arxiv.org/abs/2506.13611

A Hybrid Artificial Intelligence Method for Estimating Flicker in Power Systems
This paper introduces a novel hybrid AI method combining H filtering and an adaptive linear neuron network for flicker component estimation in power distribution systems.The proposed method leverages the robustness of the H filter to extract the voltage envelope under uncertain and noisy conditions followed by the use of ADALINE to accurately identify flicker frequencies embedded in the envelope.This synergy enables efficient time domain estimation with rapid convergence and noise resilience ad…

Evolutionary chemical learning in dimerization networks
Alexei V. Tkachenko, Bortolo Matteo Mognetti, Sergei Maslov
https://arxiv.org/abs/2506.14006 https:…

Evolutionary chemical learning in dimerization networks
We present a novel framework for chemical learning based on Competitive Dimerization Networks (CDNs) - systems in which multiple molecular species, e.g. proteins or DNA/RNA oligomers, reversibly bind to form dimers. We show that these networks can be trained in vitro through directed evolution, enabling the implementation of complex learning tasks such as multiclass classification without digital hardware or explicit parameter tuning. Each molecular species functions analogously to a neuron, wi…

Integer Binary-Range Alignment Neuron for Spiking Neural Networks
Binghao Ye, Wenjuan Li, Dong Wang, Man Yao, Bing Li, Weiming Hu, Dong Liang, Kun Shang
https://arxiv.org/abs/2506.05679

Integer Binary-Range Alignment Neuron for Spiking Neural Networks
Spiking Neural Networks (SNNs) are noted for their brain-like computation and energy efficiency, but their performance lags behind Artificial Neural Networks (ANNs) in tasks like image classification and object detection due to the limited representational capacity. To address this, we propose a novel spiking neuron, Integer Binary-Range Alignment Leaky Integrate-and-Fire to exponentially expand the information expression capacity of spiking neurons with only a slight energy increase. This is a…

Decision-making in light-trapped slime molds involves active mechanical processes
Lisa Schick, Emily Eichenlaub, Fabian Drexel, Alexander Mayer, Siyu Chen, Marcus Roper, Karen Alim
https://arxiv.org/abs/2506.12803

Decision-making in light-trapped slime molds involves active mechanical processes
Decision-making is the process of selecting an action among alternatives, allowing biological and artificial systems to navigate complex environments and optimize behavior. While neural systems rely on neuron-based sensory processing and evaluation, decision-making also occurs in organisms without a centralized organizing unit, such as the unicellular slime mold \textit{Physarum polycephalum}. Unlike neural systems, P. polycephalum relies on rhythmic peristaltic contractions to drive internal f…

Stable Synchronous Propagation in Feedforward Networks for Biped Locomotion
Ian Stewart, David Wood
https://arxiv.org/abs/2506.11780 https://

Stable Synchronous Propagation in Feedforward Networks for Biped Locomotion
Rhythmic gait patterns in animal locomotion are widely believed to be produced by a central pattern generator (CPG), a network of neurons that drives the muscle groups. In previous papers we have discussed how phase-synchronous signals can propagate along chains of neurons using a feedforward lift of the CPG, given sufficient conditions for stability to synchrony-breaking perturbations, and shown that stable signals are common for four standard neuron models. Here we apply these ideas to bipe…

Convergent and divergent connectivity patterns of the arcuate fasciculus in macaques and humans
Jiahao Huang, Ruifeng Li, Wenwen Yu, Anan Li, Xiangning Li, Mingchao Yan, Lei Xie, Qingrun Zeng, Xueyan Jia, Shuxin Wang, Ronghui Ju, Feng Chen, Qingming Luo, Hui Gong, Xiaoquan Yang, Yuanjing Feng, Zheng Wang
https://arxiv.org/abs/25…

Convergent and divergent connectivity patterns of the arcuate fasciculus in macaques and humans
The organization and connectivity of the arcuate fasciculus (AF) in nonhuman primates remain contentious, especially concerning how its anatomy diverges from that of humans. Here, we combined cross-scale single-neuron tracing - using viral-based genetic labeling and fluorescence micro-optical sectioning tomography in macaques (n = 4; age 3 - 11 years) - with whole-brain tractography from 11.7T diffusion MRI. Complemented by spectral embedding analysis of 7.0T MRI in humans, we performed a compa…

Minimal Neuron Circuits -- Part I: Resonators
Amr Nabil, T. Nandha Kumar, Haider Abbas F. Almurib
https://arxiv.org/abs/2506.02341 https://

Minimal Neuron Circuits -- Part I: Resonators
Spiking Neural Networks have earned increased recognition in recent years owing to their biological plausibility and event-driven computation. Spiking neurons are the fundamental building components of Spiking Neural Networks. Those neurons act as computational units that determine the decision to fire an action potential. This work presents a methodology to implement biologically plausible yet scalable spiking neurons in hardware. We show that it is more efficient to design neurons that mimic …

Neuromorphic Online Clustering and Its Application to Spike Sorting
James E. Smith
https://arxiv.org/abs/2506.12555 https://arxiv.org…

Neuromorphic Online Clustering and Its Application to Spike Sorting
Active dendrites are the basis for biologically plausible neural networks possessing many desirable features of the biological brain including flexibility, dynamic adaptability, and energy efficiency. A formulation for active dendrites using the notational language of conventional machine learning is put forward as an alternative to a spiking neuron formulation. Based on this formulation, neuromorphic dendrites are developed as basic neural building blocks capable of dynamic online clustering. …

A Neuronal Model at the Edge of Criticality: An Ising-Inspired Approach to Brain Dynamics
Sajedeh Sarmastani, Maliheh Ghodrat, Yousef Jamali
https://arxiv.org/abs/2506.07027

A Neuronal Model at the Edge of Criticality: An Ising-Inspired Approach to Brain Dynamics
We present a neuronal network model inspired by the Ising model, where each neuron is a binary spin ($s_i = \pm1$) interacting with its neighbors on a 2D lattice. Updates are asynchronous and follow Metropolis dynamics, with a temperature-like parameter $T$ introducing stochasticity. To incorporate physiological realism, each neuron includes fixed on/off durations, mimicking the refractory period found in real neurons. These counters prevent immediate reactivation, adding biologically grounde…

Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder
Qi Xin, Robert E. Kass
https://arxiv.org/abs/2506.02263

Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder
Advances in large-scale recording technologies now enable simultaneous measurements from multiple brain areas, offering new opportunities to study signal transmission across interacting components of neural circuits. However, neural responses exhibit substantial trial-to-trial variability, often driven by unobserved factors such as subtle changes in animal behavior or internal states. To prevent evolving background dynamics from contaminating identification of functional coupling, we developed …

Characterizing Neural Manifolds' Properties and Curvatures using Normalizing Flows
Peter Bouss, Sandra Nester, Kirsten Fischer, Claudia Merger, Alexandre Ren\'e, Moritz Helias
https://arxiv.org/abs/2506.12187

Characterizing Neural Manifolds' Properties and Curvatures using Normalizing Flows
Neuronal activity is found to lie on low-dimensional manifolds embedded within the high-dimensional neuron space. Variants of principal component analysis are frequently employed to assess these manifolds. These methods are, however, limited by assuming a Gaussian data distribution and a flat manifold. In this study, we introduce a method designed to satisfy three core objectives: (1) extract coordinated activity across neurons, described either statistically as correlations or geometrically as…

Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
Maxime Fabre, Lyubov Dudchenko, Emre Neftci
https://arxiv.org/abs/2506.06374

Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
Multi-state spiking neurons such as the adaptive leaky integrate-and-fire (AdLIF) neuron offer compelling alternatives to conventional deep learning models thanks to their sparse binary activations, second-order nonlinear recurrent dynamics, and efficient hardware realizations. However, such internal dynamics can cause instabilities during inference and training, often limiting performance and scalability. Meanwhile, state space models (SSMs) excel in long sequence processing using linear state…

A Practical Guide to Tuning Spiking Neuronal Dynamics
William Gebhardt, Alexander G. Ororbia, Nathan McDonald, Clare Thiem, Jack Lombardi
https://arxiv.org/abs/2506.08138

A Practical Guide to Tuning Spiking Neuronal Dynamics
In this work, we examine fundamental elements of spiking neural networks (SNNs) as well as how to tune them. Concretely, we focus on two different foundational neuronal units utilized in SNNs -- the leaky integrate-and-fire (LIF) and the resonate-and-fire (RAF) neuron. We explore key equations and how hyperparameter values affect behavior. Beyond hyperparameters, we discuss other important design elements of SNNs -- the choice of input encoding and the setup for excitatory-inhibitory population…

Learning to cluster neuronal function
Nina S. Nellen, Polina Turishcheva, Michaela Vystr\v{c}ilov\'a, Shashwat Sridhar, Tim Gollisch, Andreas S. Tolias, Alexander S. Ecker
https://arxiv.org/abs/2506.03293

Learning to cluster neuronal function
Deep neural networks trained to predict neural activity from visual input and behaviour have shown great potential to serve as digital twins of the visual cortex. Per-neuron embeddings derived from these models could potentially be used to map the functional landscape or identify cell types. However, state-of-the-art predictive models of mouse V1 do not generate functional embeddings that exhibit clear clustering patterns which would correspond to cell types. This raises the question whether th…