7 citations · 10 across the 5 of their papers we have counts for
6 papers
Softmax-Free Attention in Spiking Transformers as the Zero-Temperature Limit of Two-Level Systems
Roberto C. Sotero, Pouya Taghipour, Jose M. Sanchez-Bornot
Spiking Transformers achieve energy efficiency by discarding softmax normalization in favor of thresholded, binary attention. However, this removal breaks the thermodynamic framewo…
Tunnelling Through Time Series: A Probabilistic Visibility Graph for Local and Global Pattern Discovery
Roberto Sotero, Jose Sanchez-Bornot
The growing availability of high-resolution, long-term time series data has highlighted the need for methods capable of capturing both local and global patterns. To address this, w…
Towards improving Alzheimer's intervention: a machine learning approach for biomarker detection through combining MEG and MRI pipelines
Alwani Liyana Ahmad, Jose Sanchez-Bornot, Roberto C. Sotero +3
MEG are non invasive neuroimaging techniques with excellent temporal and spatial resolution, crucial for studying brain function in dementia and Alzheimer Disease. They identify ch…
A Machine Learning Approach for Identifying Anatomical Biomarkers of Early Mild Cognitive Impairment
Alwani Liyana Ahmad, Jose Sanchez-Bornot, Roberto C. Sotero +3
Alzheimer Disease poses a significant challenge, necessitating early detection for effective intervention. MRI is a key neuroimaging tool due to its ease of use and cost effectiven…
Solving large-scale MEG/EEG source localization and functional connectivity problems simultaneously using state-space models
Jose M. Sanchez-Bornot, Roberto C. Sotero, Scott Kelso +1
State-space models are widely employed across various research disciplines to study unobserved dynamics. Conventional estimation techniques, such as Kalman filtering and expectatio…
Cross-frequency interactions during diffusion on complex brain networks are facilitated by scale-free properties
Roberto C. Sotero, Lazaro M. Sanchez-Rodriguez, Mehdy Dousty +2
We studied the interactions between different temporal scales of diffusion processes on complex networks and found them to be stronger in scale-free (SF) than in Erdos-Renyi (ER) n…