Spiking neural networks
PulseAugur coverage of Spiking neural networks — every cluster mentioning Spiking neural networks across labs, papers, and developer communities, ranked by signal.
- instance of artificial neural network 90%
- instance of ScienceCast 90%
- instance of SNNS 90%
- used by snnTorch 90%
- instance of spiking neural network 90%
- instance of SpikeYOLO 90%
- instance of Gotit.pub 90%
- developed by SpikeYOLO 90%
- instance of Leaky Integrate and Fire Neuron by Charge-Discharge Dynamics in Floating-Body MOSFET. 90%
- competes with artificial neural network 70%
- instance of alphaXiv 70%
- instance of snnTorch 70%
9 day(s) with sentiment data
-
Mask IPL enhances event-based tracking with noise-free position learning
Researchers have introduced Mask IPL, a novel method for noise-free intrinsic position learning in event-based spike-driven tracking. This technique enhances the effectiveness of Spiking Neural Networks (SNNs) by analyz…
-
AI research explores "napping" for neural networks to balance accuracy and complexity
Researchers have explored a novel "napping paradigm" for Recurrent Spiking Neural Networks (SNNs), drawing inspiration from biological sleep mechanisms. This approach combines proportional weight scaling with continuous…
-
New framework maps cyber events to spiking neural networks for anomaly detection
Researchers have developed a novel event-native symbolic-temporal spike encoding framework designed for heterogeneous cyber streams. This framework maps diverse cyber events directly into sparse, spike-compatible inputs…
-
New Supervised Hebbian Learning Algorithm for Spiking Neural Networks Outperforms STDP
Researchers have developed a new gradient-free supervised learning algorithm for spiking neural networks (SNNs) called Supervised Spike Agreement-Dependent Plasticity (Supervised SADP). This method directly embeds class…
-
New NIO Bench framework evaluates storage performance for ML workloads
A new framework called NIO Bench has been developed to evaluate the storage system performance for various machine learning workloads. The framework analyzes six diverse ML model architectures, including language transf…
-
New gradient tunneling algorithm solves feedback learning in neural microcircuits
Researchers have developed a novel gradient tunneling (GT) algorithm to address the challenge of temporal credit assignment in neural microcircuits (NMCs). This new framework, utilizing the lead-lag expansion technique,…
-
New framework compares ANN and SNN energy efficiency
A new analytical framework has been developed to compare the energy efficiency of artificial neural networks (ANNs) and spiking neural networks (SNNs) for time-series data. The framework normalizes for expressivity, rev…
-
Neuromorphic speech recognition achieves 99.77% accuracy using novel spike encoding
Researchers have developed a novel method for efficient neuromorphic speech recognition by encoding audio data into spikes for processing by Spiking Neural Networks (SNNs). This approach aims to reduce the energy consum…
-
New Spiking Neural Network for Cochlear Implants Dramatically Cuts Energy Use
Researchers have developed a new Spiking Neural Network (SNN) model for cochlear implants that significantly reduces energy consumption while maintaining speech enhancement performance. This SNN, inspired by the Deep AC…
-
New ANTShapes Datasets Advance Event-Based Neuromorphic Object Classification
Researchers have introduced ANTShapes, a simulation tool designed to generate and label event-based vision datasets for object classification. This paper presents four new datasets created with ANTShapes, which are then…
-
Spiking Neural Networks show edge in wireless sensing, new benchmark finds
A new benchmark evaluates Spiking Neural Networks (SNNs) against conventional Artificial Neural Networks (ANNs) across five sensing modalities on edge devices. The study reveals that SNNs offer comparable performance to…
-
New MeMark technique embeds watermarks in SNN neuron states
Researchers have developed a new watermarking technique called MeMark for Spiking Neural Networks (SNNs) to protect against unauthorized reuse of pre-trained models. Unlike previous methods that focused on output verifi…
-
New M-HySMap framework optimizes spiking neural network mapping
Researchers have developed M-HySMap, a new framework for mapping spiking neural networks (SNNs) onto many-core neuromorphic platforms. This approach utilizes a route-aware, activity-weighted multicast hypergraph mapping…
-
Spiking Neural Networks Offer Energy-Efficient Object Detection for Autonomous Underwater Vehicles
Researchers have developed SpikeYOLO, a novel spiking neural network (SNN) designed for energy-efficient object detection in forward-looking sonar imagery. This approach offers significant energy savings compared to tra…
-
Spiking neural networks show comparable performance to traditional RL algorithms
Researchers have developed a Spiking Actor Network Soft Actor Critic (SANSAC) algorithm, a variant of the Soft Actor-Critic (SAC) reinforcement learning method. This new algorithm is designed to be compatible with neuro…
-
New IPZO architecture enhances SNN fine-tuning on IMC accelerators
Researchers have developed an Event-triggered Implicit Perturbation (IPZO) architecture to improve the efficiency of fine-tuning spiking neural networks (SNNs) on in-memory computing (IMC) accelerators. This new approac…
-
New noisy group neuron model boosts spiking neural network performance
Researchers have introduced a novel noisy group neuron (NGN) model designed to enhance the performance of spiking neural networks (SNNs). This model integrates population-level synchronous resetting and neural stochasti…
-
Spikformer V2 achieves 80%+ accuracy on ImageNet using SNNs
Researchers have developed Spikformer V2, a novel Spiking Neural Network (SNN) that incorporates a Spiking Self-Attention mechanism. This advancement allows SNNs to leverage the performance benefits of self-attention, p…
-
New Noisy Group Neuron Method Enhances Spiking Neural Network Performance
Researchers have developed a new method called Noisy Group Neurons (NGN) to improve the training of Spiking Neural Networks (SNNs). This approach addresses challenges like spatiotemporal information loss and gradient mi…
-
New SAGE method improves Spiking Transformer training with adaptive gradients · 2 sources tracked
Researchers have introduced SAGE, a novel surrogate-gradient mechanism designed to improve the training of Spiking Transformers. This method leverages attention-guided entropy to adapt the surrogate-gradient slope durin…