spiking neural network
PulseAugur coverage of spiking neural network — every cluster mentioning spiking neural network across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
Spiking Neural Network Framework Achieves State-of-the-Art Optical Flow
Researchers have developed SICAF, a novel framework for self-supervised event-based optical flow estimation using spiking neural networks. This approach addresses challenges in extracting spatiotemporal features from ir…
-
Spiking neural networks achieve high accuracy in autonomous driving with low energy use
Researchers have developed SDPAD, a novel pipeline for end-to-end autonomous driving that utilizes spiking neural networks (SNNs) to achieve high accuracy with significantly reduced energy consumption. This approach con…
-
New Spiking Neural Network Enhances Remote Sensing Image Dehazing
Researchers have developed a new spiking neural network (SNN) called EM-SNN, designed to improve the process of removing haze from remote sensing images. Traditional SNNs struggle with the loss of detail caused by haze,…
-
Neuromorphic PRNGs achieve low power and high quality
Researchers have developed a novel neuromorphic pseudo-random number generator (NPRNG) that leverages the brain's efficient generation of unpredictable sequences. This new NPRNG is built upon a balanced spiking neural n…
-
BLADE framework optimizes hybrid SNN-ANN for reliable edge AI object detection
Researchers have developed BLADE, a novel methodology for selecting the boundary between Spiking Neural Networks (SNNs) and Artificial Neural Networks (ANNs) in event-based object detection. Unlike previous approaches t…
-
AI models compared for wingbeat counting in flapping-wing vehicles
Researchers have evaluated three types of temporal models—convolutional, spiking, and attention-based—for counting wingbeats in flapping-wing vehicles using optical flow data. The study, conducted in the MuJoCo simulati…
-
New research explores nearest neighbor methods for matrix completion · 2 papers tracked
Two new research papers introduce novel approaches to matrix completion, a technique used to fill in missing data points. The first paper, "N$^2$: A Unified Python Package and Test Bench for Nearest Neighbor-Based Matri…
-
NeuroFlex enables lossless ANN-SNN co-execution for efficient sparse inference
Researchers have developed NeuroFlex, a novel accelerator design that allows for the co-execution of artificial neural networks (ANNs) and spiking neural networks (SNNs) at the element level. This approach enables each …
-
Hybrid SNN-XGBoost architecture boosts cyber-physical system resilience
Researchers have developed a novel hybrid Spiking Neural Network (SNN) and XGBoost architecture designed to enhance the robustness of industrial cyber-physical classification systems against machine unlearning attacks. …
-
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 simulator RT-NuSIS models neuromorphic spectrum intelligence
Researchers have developed a new simulator called RT-NuSIS, designed to study spiking neural networks (SNNs) and memristor-inspired agents. This framework focuses on dynamic spectrum access under challenging conditions,…
-
New framework enables efficient onboard cloud removal for LEO satellites
Researchers have developed ORBITALIF, a novel federated learning framework designed for efficient onboard cloud removal from satellite imagery. This system utilizes a compact spiking neural network (SNN) with adaptive g…
-
E-S2Feat framework enhances event-based local feature detection
Researchers have developed E-S2Feat, a novel spiking neural network framework designed for event-based local feature detection and description. This method enhances feature representation by using a spiking activation m…
-
New arXiv papers explore disconnect between neural network computation and learning
Two new arXiv papers explore the dynamics of neural computation, focusing on the divergence between complex forward computation and simpler learning mechanisms. The first paper introduces a "Generation-Fact Graph" to un…
-
New method improves ANN-SNN conversion accuracy and speed
Researchers have developed a new method to improve the conversion of Artificial Neural Networks (ANNs) to Spiking Neural Networks (SNNs), addressing accuracy drops and inference delays. The proposed strategy involves dy…
-
SpikeRestormer: Energy-Efficient AI for Image Restoration Using Spiking Neural Networks
Researchers have developed SpikeRestormer, a novel Spiking Neural Network (SNN) designed for energy-efficient All-in-One Image Restoration (AiOIR). Traditional artificial neural network (ANN) methods for AiOIR are compu…
-
Mineng Technology secures funding for brain-like SNN chips in medical devices
Mineng Technology has secured tens of millions in funding to advance its self-developed Spiking Neural Network (SNN) chips, designed to serve as the core processing unit for medical devices. These chips mimic the brain'…
-
Bio-inspired Transformer Enhances HDR Image Reconstruction
Researchers have developed Bio-SFT, a novel bio-inspired spiking frequency transformer designed for reconstructing high dynamic range (HDR) images from standard dynamic range inputs. The system incorporates three key bi…
-
Neuromorphic processor enables energy-efficient object pose estimation
Researchers have developed a novel formulation for robust Perspective-n-Point (PnP) that can be executed on neuromorphic processors, enhancing energy efficiency for object pose estimation in robotic perception. This met…
-
EEG seizure detection models made efficient with quantization and pruning
Researchers have developed methods to make deep neural networks more efficient for detecting seizures from EEG data. They explored converting a CNN into a spiking neural network, pruning EEG channels, and using INT8 qua…