Unverified50% confidenceFactExact time
ScaleBrain introduces a multi-scale EEG tokenization method that represents the same EEG signal through analysis windows of different time spans and shared temporal anchors, so that the model input naturally possesses scale structure.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/11/2026
First Seen
Valid until: 2/9/2027
Sources
Related Entities
Related Claims
UnverifiedAxial attention has mature applications in video understanding and high-dimensional image generation, and ScaleBrain transfers it to EEG multi-scale representation fusion.75% similarUnverifiedScaleBrain designs an axial spatio-temporal attention mechanism that performs context modeling on the fused multi-scale representations along both the spatial and temporal dimensions, capturing inter-electrode spatial correlations and temporal dynamic dependencies respectively.71% similarUnverifiedThe tool's graphical interface displays in real time the loss changes per mini-batch and epoch, the gradient norm of each layer, the percentage of dead neurons, weight distribution comparisons, and first-layer receptive field visualizations.64% similarUnverifiedStandard self-attention performs fully connected attention over all fused tokens, with computation growing quadratically with the number of tokens, and since the electrode dimension and temporal dimension of EEG have different semantics, direct mixed modeling easily causes confusion.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1157914API
curl https://kongchang.com/api/v1/knowledge/claims/1157914MCP
get_claim(id=1157914)