Tyler Bonnen

• Approximating Human-Level 3D Visual Inferences With Deep Neural Networks

  Open Access•Thomas O’Connell, Thomas P O’Connell et al.•ARTICLE•Open MIND•2025

  Añadir item

  Humans make rich inferences about the geometry of the visual world. While deep neural networks (DNNs) achieve human-level performance on some psychophysical tasks (e.g., rapid classification of object or scene categories), they often fail in tasks requiring inferences about the underlying shape of objects or scenes. Here, we ask whether and how this gap in 3D shape representation between DNNs and humans can be closed. First, we define the problem…

• Medial temporal cortex supports object perception by integrating over visuospatial sequences

  Open Access•Tyler Bonnen, Anthony D Wagner et al.•ARTICLE•Cognition•2025

  Añadir item

• Approximating Human-Level 3D Visual Inferences With Deep Neural Networks

  Open Access•Thomas O’Connell, Thomas P O’Connell et al.•ARTICLE•Open MIND•2025

  Añadir item

  Humans make rich inferences about the geometry of the visual world. While deep neural networks (DNNs) achieve human-level performance on some psychophysical tasks (e.g., rapid classification of object or scene categories), they often fail in tasks requiring inferences about the underlying shape of objects or scenes. Here, we ask whether and how this gap in 3D shape representation between DNNs and humans can be closed. First, we define the problem…

• Medial temporal cortex supports object perception by integrating over visuospatial sequences

  Open Access•Tyler Bonnen, Anthony D Wagner et al.•ARTICLE•Cognition•2025

  Añadir item

Visual perception and processing mechanisms (2 obras) · 3D Shape Modeling and Analysis (1 obra) · Advanced Vision and Imaging (1 obra) · Artificial Intelligence (1 obra) · Artificial neural network (1 obra) · Autoencoder (1 obra) · Cognition (1 obra) · Cognitive neuroscience of visual object recognition (1 obra) · Cognitive psychology (1 obra) · Cognitive science (1 obra)