visual system
High resolution neural connectivity from incomplete tracing data using nonnegative spline regression
Whole-brain neural connectivity data are now available from viral tracing experiments, which reveal the connections between a source injection site and elsewhere in the brain.
Curriculum Learning with Infant Egocentric Videos
Infants possess a remarkable ability to rapidly learn and process visual inputs.
- Health & Medicine > Therapeutic Area > Neurology (0.94)
- Education (0.93)
Surround Modulation: A Bio-inspired Connectivity Structure for Convolutional Neural Networks
Hosein Hasani, Mahdieh Soleymani, Hamid Aghajan
Neural Information Processing Systems http://nips.cc/
- North America > Canada (0.04)
- Asia > Japan > Honshū > Tōhoku > Fukushima Prefecture > Fukushima (0.04)
Task-Driven Convolutional Recurrent Models of the Visual System
Aran Nayebi, Daniel Bear, Jonas Kubilius, Kohitij Kar, Surya Ganguli, David Sussillo, James J. DiCarlo, Daniel L. Yamins
Neural Information Processing Systems http://nips.cc/
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.14)
- North America > United States > California > Santa Clara County > Stanford (0.05)
- Europe > Belgium > Flanders > Flemish Brabant > Leuven (0.04)
- (3 more...)
Generalisation in humans and deep neural networks
Robert Geirhos, Carlos R. M. Temme, Jonas Rauber, Heiko H. Schütt, Matthias Bethge, Felix A. Wichmann
Neural Information Processing Systems http://nips.cc/
- Europe > United Kingdom > England > Oxfordshire > Oxford (0.14)
- Europe > Austria > Vienna (0.14)
- Europe > Germany > Baden-Württemberg > Tübingen Region > Tübingen (0.05)
- (3 more...)
- North America > United States > California > Los Angeles County > Los Angeles (0.14)
- Oceania > Australia > Victoria > Melbourne (0.04)
- North America > United States > New York > Suffolk County > Huntington (0.04)
- (2 more...)
- Research Report > Experimental Study (0.69)
- Research Report > New Finding (0.47)
Energy Guided Diffusion for Generating Neurally Exciting Images
In recent years, most exciting inputs (MEIs) synthesized from encoding models of neuronal activity have become an established method for studying tuning properties of biological and artificial visual systems. However, as we move up the visual hierarchy, the complexity of neuronal computations increases. Consequently, it becomes more challenging to model neuronal activity, requiring more complex models. In this study, we introduce a novel readout architecture inspired by the mechanism of visual attention. This new architecture, which we call attention readout, together with a data-driven convolutional core outperforms previous task-driven models in predicting the activity of neurons in macaque area V4.