Learning viewpoint-invariant face representations from visual experience in an attractor network

DOI10.1088/0954-898X/9/3/008zbMath0904.92041OpenAlexW4237768773MaRDI QIDQ4211343

Terrence J. Sejnowski, Marian Stewart Bartlett

Publication date: 14 January 1999

Full work available at URL: https://doi.org/10.1088/0954-898x/9/3/008

zbMATH Keywords

Hopfield networksimulationsHebbian learningfeedforward connectionsrecurrent layerviewpoint-invariant representations of faces

Mathematics Subject Classification ID

Memory and learning in psychology (91E40) Psychophysics and psychophysiology; perception (91E30)

Related Items (11)

Recognition invariance obtained by extended and invariant features ⋮ Learning invariant object recognition in the visual system with continuous transformations ⋮ A Taxonomy for Spatiotemporal Connectionist Networks Revisited: The Unsupervised Case ⋮ Towards cortex sized artificial neural systems ⋮ Fast and Robust Learning by Reinforcement Signals: Explorations in the Insect Brain ⋮ A Canonical Neural Circuit for Cortical Nonlinear Operations ⋮ Slow Feature Analysis: Unsupervised Learning of Invariances ⋮ Learning invariant face recognition from examples ⋮ Attractor Networks for Shape Recognition ⋮ Invariant Global Motion Recognition in the Dorsal Visual System: A Unifying Theory ⋮ GENOMIC ORGANIZATION AND HOPFIELD'S MODEL OF ASSOCIATIVE MEMORY

This page was built for publication: Learning viewpoint-invariant face representations from visual experience in an attractor network