3 papers
cs.LG2026
Isolating Nonlinear Independent Sources in fMRI with -TCVAE Models
Qiang Li, Shujian Yu, Jesus Malo +3
Learning meaningful latent representations from nonlinear fMRI data remains a fundamental challenge in neuroimaging analysis. Traditional independent component analysis, widely use…
cs.CV2026
Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs
Nuria Alabau-Bosque, Jorge Vila-Tomas, Paula Dauden-Oliver +2
Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility: even a single-pixel shift can drastic…
q-bio.NC2026
Information in a recurrent Retina-V1 network with realistic noise, feedback and nonlinearities
Javier RodrÃguez, Raquel Giménez, Jesús Malo
Quantitative estimation of information flow in early vision with psychophysically realistic networks is still an open issue. This is because, up to date, the necessary elements (ge…