arXiv AI

A Variational Latent Equilibrium for Learning in Neuronal Circuits

The paper proposes a biologically plausible framework to approximate backpropagation through time (BPTT) for learning complex temporal dependencies in neuronal circuits. It derives a time‑continuous equivalent of BPTT using a prospective energy function and introduces a learning rule for backward weights that ensures fully local space‑time dynamics, correcting gain errors inherent in previous approximations. This approach unifies and extends prior local, phase‑free credit assignment methods, offering a rigorous basis for spatiotemporal deep learning in the brain and guiding the design of physical circuits that implement these computations.

arXiv AI
Sep 25

ELiSe: Efficient Learning of Sequences in Structured Recurrent Networks

The paper introduces ELiSe, a model that leverages cortical network scaffolds and dendritic compartments to learn complex non‑Markovian spatio‑temporal patterns using only local, always‑on, phase‑free synaptic plasticity. It demonstrates the model’s ability to acquire and replay intricate sequences, exemplified by a birdsong learning mock‑up, and shows robustness to external disturbances and flexibility in parameter settings.

By Laura Kriener, Kristin V\"olk, Ben von H\"unerbein, Federico Benitez, Walter Senn, Mihai A. Petrovici
arXiv Machine Learning
1d ago

Local Spike Timing Enables Gradient-based Learning in Neural Microcircuits

The paper introduces a new framework that reconciles discrete spike timing with continuous gradient-based learning in neural microcircuits (NMCs). By reformulating temporal credit assignment as a state‑separation problem, the authors develop a gradient‑tunneling (GT) algorithm and lead‑lag expansion technique that derive learning signals directly from local synaptic spike timing. Experiments show that GT‑trained NMCs achieve strong performance on long‑timescale evidence integration, noise‑robust memory retention, and real‑world benchmarks while using far fewer parameters than existing spiking neural network methods.

By Xiangnan Zhang, Jingxin Liu, Ranqi Lu, Jingyu Liu, Qunxi Dong, Fuze Tian, Lixian Zhu, Bin Hu, Bj\"orn W. Schuller
arXiv Machine Learning
1d ago

Identifying Latent Neural Dynamics with Recognition-Parametrised Gaussian Process Dynamical Systems

The paper introduces the Recognition-Parametrised Gaussian Process dynamics (RP‑GPdyn) model, which avoids explicit generative parameterisations by using a nonparametric Gaussian Process to define the dynamical flow field and an implicit mapping to neural activity via the Recognition‑Parametrised Model framework. This generation‑free approach is shown to recover meaningful, behaviourally relevant latent variables and dynamics from both synthetic and experimental neural datasets. The method addresses potential biases arising from misspecification of dynamical flow, state‑to‑activity mapping, or neural response variability.

By Arielle Rosinski, Qianqian Feng, Lior Fox, Maneesh Sahani
arXiv Computer Vision
Oct 16

The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks

The paper introduces the Dormant Spiking Neuron (DSN), a state-driven mechanism that allows neurons in spiking neural networks to enter a dormant state when their membrane potential falls below a negative threshold. This dynamic gating prunes redundant computations at the instance level and is trained end‑to‑end via backpropagation through time with surrogate gradients. Experiments on static and neuromorphic datasets, including ImageNet, show that DSN reduces computational energy by 40% to over 70% and improves baseline SNN accuracy by 1.34%, outperforming state‑of‑the‑art static pruning methods.

By Ruichen Ma, Yicai Chen, Pujun Zhou, Yue Zuo, Chongyang Li, Shuang Liu, Shaogang Hu, Guanchao Qiao
arXiv AI
Jun 2

Equilibrium Propagation for Non-Conservative Systems

arXiv:2602. 03670v2 Announce Type: replace-cross Abstract: Equilibrium Propagation (EP) is a physics-inspired learning algorithm that uses stationary states of a dynamical system both for inference and learning.

By Antonino Emanuele Scurria, Dimitri Vanden Abeele, Bortolo Matteo Mognetti, Serge Massar