On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “LIF”

Locally Imposing Function for Generalized Constraint Neural Networks - A Study on Equality Constraintscs.NE

A new method LIF for equality constraints in GCNN models is proposed.

problem Embedding and selecting imposing schemes for prior information in GCNN models.

method Locally Imposing Function (LIF) for equality constraints.

result LIF enables local and explicit constraint implementation in the domain.

GCNN equality constraints Locally Imposing Scheme LIF LIS

2016-04-18abs ↗pdf ↗

Random Spiking Neural Networks are Stable and Spectrally Simplecs.LG

Random SNNs are stable and simple, with low-frequency Fourier spectra.

problem Stability and robustness of spiking neural networks.

method Boolean function analysis and Fourier spectrum concentration.

result Random LIF-SNNs are stable and biased towards simple functions.

spiking neural networks stability robustness Fourier spectrum Boolean functions

2025-11-02abs ↗pdf ↗

SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networksq-bio.NC

SparseProp speeds up SNN simulations and training by four orders of magnitude.

problem Efficiently simulating and training large spiking neural networks.

method Event-based algorithm that reduces computational cost from O(N) to O(log(N)) per spike.

result Numerically exact simulations of large spiking networks and efficient training using backpropagation.

spiking neural networks sparse recurrent networks event-based simulation backpropagation action potentials

2023-12-28abs ↗pdf ↗

Bridging Theory and Practice in Crafting Robust Spiking Reservoirscs.LG

This work bridges theory and practice in spiking reservoirs, identifying robust parameter ranges.

problem Challenging tuning of spiking reservoirs at the edge-of-chaos.

method Introducing robustness interval, systematic evaluations, and control experiments.

result Consistent monotonic trends in robustness interval width across network configurations.

spiking reservoirs edge-of-chaos robustness interval hyperparameter search Leaky Integrate-and-Fire

2026-04-07abs ↗pdf ↗

Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscs.NE

New method trains SNNs with spatio-temporal backpropagation.

problem Training SNNs with spatio-temporal information.

method Iterative LIF model, spatio-temporal backpropagation (STBP).

result Best performance on static and dynamic MNIST datasets.

spiking neural networks backpropagation spatio-temporal gradient descent neural networks

2017-06-08abs ↗pdf ↗

DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networkscs.NE

DIET-SNN optimizes SNNs for faster, lower-energy image classification.

problem High inference latency and inefficient input encoding in SNNs.

method End-to-end backpropagation to optimize membrane leak and firing threshold.

result Achieves top-1 accuracy of 69% on ImageNet with 5 timesteps and 12x less compute energy.

spiking neural networks deep learning image classification energy efficiency inference latency

2020-08-09abs ↗pdf ↗

The high-conductance state enables neural sampling in networks of LIF neuronsq-bio.NC

New approach shows how neurons can perform sampling inference in high-conductance state.

problem How to perform sample-based inference in networks of spiking neurons.

method Separate modes of spiking dynamics: burst spiking and transient quiescence. Used PDF propagation for bursts and diffusion approximation for quiescence. Analyzed high-conductance state (HCS) for neural response function.

result Neural response function becomes symmetric and can be approximated by a logistic function in HCS, enabling neural sampling.

neural sampling neuron dynamics high-conductance state Bayesian inference neuromorphic systems

2016-01-05abs ↗pdf ↗