Spiking neural networks
PulseAugur coverage of Spiking neural networks — every cluster mentioning Spiking neural networks across labs, papers, and developer communities, ranked by signal.
- developed by SpikeYOLO 95%
- instance of SpikeYOLO 95%
- instance of artificial neural network 90%
- instance of ScienceCast 90%
- instance of Leaky Integrate and Fire Neuron by Charge-Discharge Dynamics in Floating-Body MOSFET. 90%
- instance of alphaXiv 90%
- instance of neuromorphic engineering 90%
- instance of LIF 90%
- used by snnTorch 90%
- instance of spiking neural network 90%
- instance of SNNS 90%
- used by Spike-timing dependent plasticity 90%
14 day(s) with sentiment data
-
Spiking Neural Networks Study Explores IoT Sensing Efficiency
This empirical study investigates how different spike encoding methods impact the energy efficiency and accuracy of Spiking Neural Networks (SNNs) on Internet of Things (IoT) devices. Researchers analyzed various sensin…
-
New research explores local learning and continuous dynamics in Spiking Neural Networks
Two new research papers explore advancements in Spiking Neural Networks (SNNs). The first paper introduces a novel local learning framework inspired by Neural Activity Synchronization, which reduces computational comple…
-
AI framework uses neuromorphic computing for power electronics monitoring
Researchers have developed a novel AI framework for condition monitoring in power electronics, leveraging spike-based neuromorphic computing. This approach integrates neural computation with electrical circuit principle…
-
New KvLIF neuron model boosts Spiking Neural Network capacity and robustness
Researchers have developed a new neuron model called Potassium-regulated LIF (KvLIF) to improve the performance and robustness of Spiking Neural Networks (SNNs). This model, inspired by biological potassium channels, in…
-
Quantum Coherence in Neural Networks & 4D Audio-Visual Scene Generation Explored
A new study explores the use of quantum coherence within spiking neural networks to enhance proton transfer, a key process in neuromorphic computing. Separately, another development in "Technomantics" showcases the gene…
-
Quantum Physics Explores New Frontiers in Biology and Computing
Researchers are exploring the potential of quantum phenomena to advance biological and computational fields. One area of focus is harnessing quantum coherence within microtubules, which could lead to significant breakth…
-
Novel hybrid memristor architecture advances neuromorphic computing
A new paper by Dang et al. introduces a novel hybrid memristor architecture designed for neuromorphic computing. This architecture represents a significant advancement, potentially revolutionizing decision-making proces…
-
Spiking Neural Networks Advance Neuromorphic Computing with Energy-Efficient Learning
Researchers have developed Spiking Neural Networks (SNNs) that significantly advance neuromorphic computing. These SNNs demonstrate energy-efficient learning capabilities, incorporating sustained fatigue and long-term m…
-
Neuromodulation boosts accuracy in spiking neural networks on neuromorphic hardware
Researchers have developed a novel method for enhancing the performance of mixed-signal neuromorphic hardware by implementing input-dependent neuromodulation. This technique allows a fixed neural network to dynamically …
-
AI at a Turning Point: Connectionist vs. Neuromorphic Approaches Explored
A new monograph titled "AI at a Turning Point" explores the growing tension between established connectionist AI, exemplified by ChatGPT, and emerging neuromorphic AI approaches. The paper highlights the significant ene…
-
New method probes privacy risks in memristive AI hardware
Researchers have developed a new method called Spiking Domain Model Inversion (SDMI) to analyze privacy leakage in memristive spiking neural networks (SNNs). This technique combines Expectation over Transformation (EOT)…
-
New Spiking Neural Network Achieves Group Equivariance for Vision Tasks
Researchers have developed GC-LIF, a novel spiking neural network architecture that integrates group equivariance to improve performance on vision tasks. This new model, SGE-Net, addresses a key challenge in spiking neu…
-
New research explores hardware impact on AI privacy and learning
Two new arXiv papers explore the intricacies of hardware-aware model inversion and device-informed plasticity in memristive spiking neural networks (SNNs). The first paper introduces Spiking Domain Model Inversion (SDMI…
-
SpikeAD: Multiplication-Free Neuromorphic Architecture for Energy-Efficient Object Detection
Researchers have developed SpikeAD, a novel neuromorphic architecture designed for energy-efficient small object detection in aerial platforms. This architecture utilizes spiking neural networks (SNNs) with a unique app…
-
Spiking Neural Networks Show Increased Resistance to Model Stealing Attacks
A new study published on arXiv explores the security implications of Spiking Neural Networks (SNNs) compared to conventional Artificial Neural Networks (ANNs). The research benchmarks four common model stealing attacks …
-
Spiking Neural Networks: Temporal Dynamics Crucial for Privacy
Researchers have analyzed how privacy leakage occurs in Spiking Neural Networks (SNNs), which encode information in the timing of neuron firings. They found that biologically inspired, burst-like firing patterns can red…
-
New method enhances robustness of event-based spiking neural networks
Researchers have developed Perturbation-Aware Firing Scaffolds (PAFS), a novel post-training calibration method for event-based spiking neural networks (SNNs). PAFS addresses the sensitivity of SNNs to perturbations lik…
-
FPGA accelerator for Spiking Neural Networks uses minifloat arithmetic
Researchers have developed a new hardware accelerator architecture for Spiking Neural Networks (SNNs) that utilizes parameterized minifloat arithmetic. This design allows for configurable precision, enabling a trade-off…
-
New research explores functional modularity in neural networks and efficient SNN quantization
Two new research papers explore advancements in neural network architectures and efficiency. The first paper, "Sparsity-driven emergence of functional modularity in multitask neural networks," demonstrates how sparsity-…
-
Bio-inspired spiking networks achieve single-digit WER on speech recognition
Researchers have developed a novel Spiking Ternary GRU (stGRU) architecture that enhances energy efficiency and performance in automatic speech recognition (ASR). This bio-inspired model couples parallel resonate-and-fi…