Spiking attention is a universal approximator of permutation-equivariant functions with ε-approximation requiring Ω(L_f² nd / ε²) spikes, but low effective dimensions (47-89) allow T=4 timesteps in practice.
Title resolution pending
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A programmable superconducting LIF neuron with intrinsic static memory and dual-timescale plasticity achieves 45 GHz operation and femtojoule energy per spike.
SupraSNN introduces a superscalar-inspired SNN accelerator with decoupled synapse and neuron units, multi-cast/merge trees, and partitioning/scheduling that reports 47.6% lower latency and 5.6x better energy efficiency than prior FPGA SNN designs on MNIST and SHD tasks.
CLANE achieves 70.4% accuracy on continual 50-class action recognition from event cameras on Loihi 2, with novel hardware modules delivering over 100x energy reduction versus a CNN+GRU+CLP GPU baseline.
A 194M-parameter spiking dual-path model trained on 3B Chinese-English tokens achieves held-out PPL 8.88-8.93 at >89% per-element sparsity, trailing GPT-2 201M by 7.7% while showing that LIF temporal integration outperforms simple top-k masking at matched sparsity.
A neuron-astrocyte network with dual-timescale memory reduces median path lengths up to sixfold in partially observable grid-world navigation tasks.
SiLIF models apply SSM dynamics and parametrization to spiking neurons for stable training, reaching new SOTA on event-based and raw-audio speech datasets while using half the compute of SSMs via synaptic delays.
D-HTM adds a shared associative memory to hierarchical temporal memory so that precursor signatures learned on one entity can trigger preemptive warnings on related entities, yielding an average 8.1-sample lead time on tested datasets.
Open-source configurable LFSR-based stochastic LIF neuron in 130 nm CMOS with bit-exact model, stochastic characterization, and rate-coding sweeps.
Clockless FPGA circuits produce autonomous spiking neuron networks that achieve competitive audio classification accuracy with significantly lower power than conventional digital implementations.
Asynchronous sequential updates in KLR Hopfield networks produce statistically indistinguishable trajectories from synchronous dynamics, achieve empirical capacities near P/N=30, and converge with event counts close to initial Hamming distance.
Spike sparsity in VS-WNO does not reduce latency or energy on Jetson Orin Nano because the runtime executes dense work regardless of spike activity.
Olfactory-inspired signal conditioning regularizes diverse inputs so a single brain-mimetic network performs classification across gas sensing, remote sensing, and species identification without hyperparameter changes.
Presents four compatible standard-cell IP blocks for PVT sensing, stochastic LIF inference, on-chip STDP, and crossbar control in SkyWater 130 nm, verified in simulation with no silicon results reported.
citing papers explorer
-
Closing the Theory-Practice Gap in Spiking Transformers via Effective Dimension
Spiking attention is a universal approximator of permutation-equivariant functions with ε-approximation requiring Ω(L_f² nd / ε²) spikes, but low effective dimensions (47-89) allow T=4 timesteps in practice.
-
Programmable superconducting neuron with intrinsic in-memory computation and dual-timescale plasticity for ultra-efficient neuromorphic computing
A programmable superconducting LIF neuron with intrinsic static memory and dual-timescale plasticity achieves 45 GHz operation and femtojoule energy per spike.
-
SupraSNN: Exploiting Synapse-Level Parallelism in Spiking Neural Network Accelerators through Co-Optimized Mapping and Scheduling
SupraSNN introduces a superscalar-inspired SNN accelerator with decoupled synapse and neuron units, multi-cast/merge trees, and partitioning/scheduling that reports 47.6% lower latency and 5.6x better energy efficiency than prior FPGA SNN designs on MNIST and SHD tasks.
-
CLANE: Continual Learning of Actions on Neuromorphic Hardware from Event Cameras
CLANE achieves 70.4% accuracy on continual 50-class action recognition from event cameras on Loihi 2, with novel hardware modules delivering over 100x energy reduction versus a CNN+GRU+CLP GPU baseline.
-
SymbolicLight V1: Spike-Gated Dual-Path Language Modeling with High Activation Sparsity and Sub-Billion-Scale Pre-Training Evidence
A 194M-parameter spiking dual-path model trained on 3B Chinese-English tokens achieves held-out PPL 8.88-8.93 at >89% per-element sparsity, trailing GPT-2 201M by 7.7% while showing that LIF temporal integration outperforms simple top-k masking at matched sparsity.
-
Dual-Timescale Memory in a Spiking Neuron-Astrocyte Network for Efficient Navigation
A neuron-astrocyte network with dual-timescale memory reduces median path lengths up to sixfold in partially observable grid-world navigation tasks.
-
SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
SiLIF models apply SSM dynamics and parametrization to spiking neurons for stable training, reaching new SOTA on event-based and raw-audio speech datasets while using half the compute of SSMs via synaptic delays.
-
Distributed Hierarchical Temporal Memory with Shared Associative Memory for Cross-Entity Preemptive Warning
D-HTM adds a shared associative memory to hierarchical temporal memory so that precursor signatures learned on one entity can trigger preemptive warnings on related entities, yielding an average 8.1-sample lead time on tested datasets.
-
An Open-Source LFSR-Based Stochastic Leaky Integrate-and-Fire Neuron in SkyWater 130 nm: Design, Stochastic Characterisation, and Rate Coding
Open-source configurable LFSR-based stochastic LIF neuron in 130 nm CMOS with bit-exact model, stochastic characterization, and rate-coding sweeps.
-
Scalable neuromorphic computing from autonomous spiking dynamics in a clockless reconfigurable chip
Clockless FPGA circuits produce autonomous spiking neuron networks that achieve competitive audio classification accuracy with significantly lower power than conventional digital implementations.
-
Efficient event-driven retrieval in high-capacity kernel Hopfield networks
Asynchronous sequential updates in KLR Hopfield networks produce statistically indistinguishable trajectories from synchronous dynamics, achieve empirical capacities near P/N=30, and converge with event counts close to initial Hamming distance.
-
When Spike Sparsity Does Not Translate to Deployed Cost: VS-WNO on Jetson Orin Nano
Spike sparsity in VS-WNO does not reduce latency or energy on Jetson Orin Nano because the runtime executes dense work regardless of spike activity.
-
Signal Conditioning for Learning in the Wild
Olfactory-inspired signal conditioning regularizes diverse inputs so a single brain-mimetic network performs classification across gas sensing, remote sensing, and species identification without hyperparameter changes.
-
Design and Development of a Neuromorphic Silicon Suite: PVT Sensing, Stochastic LIF Inference, On-Chip STDP Learning, and Crossbar Programming
Presents four compatible standard-cell IP blocks for PVT sensing, stochastic LIF inference, on-chip STDP, and crossbar control in SkyWater 130 nm, verified in simulation with no silicon results reported.