#spiking-neural-networks News & Analysis

30 articles tagged with #spiking-neural-networks. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

30 articles

AIBullisharXiv – CS AI · Mar 176/10

🧠

Collapse or Preserve: Data-Dependent Temporal Aggregation for Spiking Neural Network Acceleration

Researchers developed Temporal Aggregated Convolution (TAC) to accelerate spiking neural networks by aggregating spike frames before convolution, achieving 13.8x speedup on rate-coded data. The study reveals that optimal temporal aggregation strategies depend on data type - collapsing temporal dimensions for rate-coded data while preserving them for event-based data.

🏢 Nvidia

AIBullisharXiv – CS AI · Mar 176/10

🧠

CATFormer: When Continual Learning Meets Spiking Transformers With Dynamic Thresholds

Researchers introduce CATFormer, a new spiking neural network architecture that solves catastrophic forgetting in continual learning through dynamic threshold neurons. The framework uses context-adaptive thresholds and task-agnostic inference to maintain knowledge across multiple learning tasks without performance degradation.

AIBullisharXiv – CS AI · Mar 36/104

🧠

Scalable Multi-Task Learning through Spiking Neural Networks with Adaptive Task-Switching Policy for Intelligent Autonomous Agents

Researchers have developed SwitchMT, a novel methodology using Spiking Neural Networks with adaptive task-switching for multi-task learning in autonomous agents. The approach addresses task interference issues and demonstrates competitive performance in multiple Atari games while maintaining low power consumption and network complexity.

AIBullisharXiv – CS AI · Feb 276/105

🧠

Spark: Modular Spiking Neural Networks

Researchers have introduced Spark, a new modular framework for spiking neural networks that aims to improve energy efficiency and data processing compared to traditional neural networks. The framework demonstrates its capabilities by solving complex problems like the sparse-reward cartpole using simple plasticity mechanisms, potentially advancing continuous learning approaches similar to biological systems.

AINeutralarXiv – CS AI · Mar 34/104

🧠

Accuracy-Efficiency Trade-Offs in Spiking Neural Networks: A Lempel-Ziv Complexity Perspective on Learning Rules

Researchers developed a framework using Lempel-Ziv complexity to evaluate trade-offs between accuracy and computational efficiency in spiking neural networks. The study found that gradient-based learning achieves highest accuracy but at high computational cost, while bio-inspired learning rules offer better efficiency trade-offs for temporal pattern recognition tasks.

← PrevPage 2 of 2