Technical Program

Paper Detail

Paper: PS-1B.42
Session: Poster Session 1B
Location: H Fläche 1.OG
Session Time: Saturday, September 14, 16:30 - 19:30
Presentation Time:Saturday, September 14, 16:30 - 19:30
Presentation: Poster
Publication: 2019 Conference on Cognitive Computational Neuroscience, 13-16 September 2019, Berlin, Germany
Paper Title: Extreme Translation Tolerance in Humans and Machines
Manuscript:  Click here to view manuscript
License: Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
Authors: Ryan Blything, University of Bristol, United Kingdom; Ivan Vankov, New Bulgarian University, Bulgaria; Casimir Ludwig, Jeffrey Bowers, University of Bristol, United Kingdom
Abstract: What mechanism supports our ability to recognize objects over a wide range of different retinal locations? Most research in psychology and neuroscience suggests that learning to identify a novel object at one retinal location only supports the ability to identify that object at nearby retinal locations, and to date, neural network models of object identification show a similar restriction in generalization. As a consequence, it is widely assumed that objects need to be learned at multiple locations. We challenge this view and show the capacity to generalize across retinal locations (what we call on-line translation tolerance) has been underestimated in humans and artificial neural networks. Two eye tracking studies demonstrate that novel objects can be recognized following translations of 9° and even 18°. Additionally, computational studies showed that convolutional neural networks can achieve similarly robust generalization when a mechanism (Global Average Pooling) was built in to generate larger receptive fields.