OBJECTPERMOD · Explaining object permanence with a deep recurrent neural network model of human cortical visual cognition
Horizon 2020 — Marie Skłodowska-Curie Actions
- Duration
- 2019-09-01 → 2023-10-17
- EU contribution
- €271,733
- Participants
- 2
- Scheme
- MSCA-IF
Lines connect the coordinator with its partners.
Results in brief
Explaining object permanence with a deep recurrent neural network model of human cortical visual cognition
Visual cognition is our ability to recognize the things we see around us and make inferences about their meaning and relationships. A hallmark step in the development of human visual cognition is the acquisition of object permanence. Object permanence is the ability to continue to mentally represent an object that has disappeared from view – for example because it is hidden behind another object. More generally, mental representations of objects that are currently not present underlie complex cognitive processes such as reasoning and planning. While object permanence is fundamental to human vision, its computational mechanisms remain a mystery. To test how these mechanisms give rise to object permanence in the brain, we need to build computational models of cortical processing. Deep convolutional neuronal network (CNN) models now achieve human-level performance on a range of visual tasks. They have advanced our understanding of human and primate visual cognition, providing a crucial link between the disciplines of psychology, neuroscience, and artificial intelligence. Current deep neural network models of vision however lack the fundamental ability of object permanence, limiting their power as models of human visual cognition and as artificially intelligent systems. This project has made significant progress in our understanding of human and machine object vision, yielded novel tasks sets for dynamic object vision and humans and machines driving progress in cognitive computational neuroscience and AI, and developed novel computational neural network models of human object perception.
Data: CORDIS, © European Union
Project objective
Visual cognition is our ability to recognize the things we see around us and make inferences about their meaning andrelationships. Deep convolutional neuronal network (CNN) models now achieve human-level performance on certain visualrecognition tasks and currently provide the most powerful models of human visual cognition. A hallmark step in thedevelopment of human visual cognition is the acquisition of object permanence (OP). Object permanence is the ability tocontinue to mentally represent an object that has disappeared from view – for example because it is hidden behind anotherobject. Current deep neural network models of vision lack this fundamental ability, limiting their power as models of humanvisual cognition and as artificially intelligent systems. In this action, I will study the computational mechanisms necessary forOP using a highly innovative approach that combines four elements: (1) a novel behavioral task that requires OP, (2)development of a deep recurrent neural network models, (3) testing of both human participants and models at the task, and(4) measurement of brain activity with functional magnetic resonance imaging (fMRI) during task performance. The OP taskinvolves viewing a scene of moving objects that occasionally become occluded behind other objects. Models will be trainedto represent objects continually, even as they vanish behind an occluder, and selected to match behavioral and cortical-layer-resolved high-field fMRI data of human observers. The hosts, Prof Kriegeskorte at Columbia University and Prof Muckliat University of Glasgow are world-leading experts on deep neural network models of vision and cortical-layer-resolved highfieldfMRI, respectively. The outcome of this action, a biologically plausible deep recurrent convolutional model that canexplain behavior and brain activity, will significantly enhance our understanding of the computational principles of visualcognition, with implications also for AI technology.
Original text from CORDIS.
Participants
- UNIVERSITY OF GLASGOW · GlasgowCoordinatorUnited Kingdom
- TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK · New YorkUnited States
Links
Data: CORDIS, © European Union