This work formalizes causal regions as polyhedral regions with fixed causal sets and derive upper and lower bounds on the maximal number of causal regions in both shallow and multilayer feedforward spiking networks.
Abstract
We study the expressivity of spiking neural networks, which provide a natural framework for asynchronous, event-driven computation complementary to conventional feedforward neural networks. We consider the time-to-first-spike model in a setting for which the input-output map is continuous and piecewise linear, with affine pieces governed by causal feasibility constraints that determine which presynaptic spikes occur before a neuron fires. We first show that each neuron's firing time admits a maxout-like representation with exponentially many, highly constrained affine pieces. We then formalize causal regions as polyhedral regions with fixed causal sets and derive upper and lower bounds on the maximal number of causal regions in both shallow and multilayer feedforward spiking networks. Our theoretical and experimental results show that spiking networks can generate richer partitions of the input space than conventional feedforward ReLU networks.
A finite stochastic spiking-neuron network with Elephant-type memory is introduced, in which past firing activity modifies future excitability through a reinforcement-dependent threshold, and non-explosion of the nonlinear process is proved.
F. Najman, I. Papageorgiou, Sabricia K. Cauanny A. da Silveira· 1 citation
SpiKFAX is proposed, a second-order optimization method that formulates a computationally tractable, Kronecker-factored approximation of the Fisher information matrix specifically adapted to the structure of SNNs.
Most ANN-to-SNN conversion methods rely on a specific correspondence between the source activation and the spiking neuron dynamics. We propose a finite-state continuous-time Markov chain (CTMC) neuron framework whose stationary spike flux can approximate every continuous nonnegative monotone activation function on a co...
Eligibility propagation (e-prop) is a biologically plausible learning rule for recurrent spiking neural networks (SNNs). It approximates gradients computed by backpropagation through time using online updates based on eligibility traces and learning signals. We reformulate the originally time-driven gradient calculatio...
A. Korcsak-Gorzo, Jesús A. Espinoza-Valverde, J. Stapmanns et al.· Neuromorphic Computing and E...· 0 citations
This work proposes a noisy group neuron (NGN) model, which incorporates population-level synchronous resetting and neural stochasticity as fundamental computational mechanisms, and develops the NGN method as a framework that combines the NGN model with backpropagation learning based on mean-field dynamics.
Yajie Zhai, Yanmei Kang, Meng Li et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026