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.
Loihi: a neuromorphic many- core processor with on-chip learning
9 Pith papers cite this work. Polarity classification is still indexing.
9
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.
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.
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.
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.
-
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.
-
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.