Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Selective Synchronization Attention
Hasi Hays
The Transformer architecture has become the foundation of modern deep learning, yet its core self-attention mechanism suffers from quadratic computational complexity and lacks grou…
cs.LG2026
Resonant Sparse Geometry Networks
Hasi Hays
We introduce Resonant Sparse Geometry Networks (RSGN), a brain-inspired architecture with self-organizing sparse hierarchical input-dependent connectivity. Unlike Transformer archi…
cs.LG2026
Attention mechanisms in neural networks
Hasi Hays
Attention mechanisms represent a fundamental paradigm shift in neural network architectures, enabling models to selectively focus on relevant portions of input sequences through le…