The origins and prevalence of texture bias in convolutional neural networks
Recent work has indicated that, unlike humans, ImageNet-trained CNNs tend to classify
images by texture rather than by shape. How pervasive is this bias, and where does it come …
images by texture rather than by shape. How pervasive is this bias, and where does it come …
[HTML][HTML] Evidence that recurrent circuits are critical to the ventral stream's execution of core object recognition behavior
Non-recurrent deep convolutional neural networks (CNNs) are currently the best at
modeling core object recognition, a behavior that is supported by the densely recurrent …
modeling core object recognition, a behavior that is supported by the densely recurrent …
Neural population control via deep image synthesis
INTRODUCTION The pattern of light that strikes the eyes is processed and re-represented
via patterns of neural activity in a “deep” series of six interconnected cortical brain areas …
via patterns of neural activity in a “deep” series of six interconnected cortical brain areas …
Representational formats of human memory traces
R Heinen, A Bierbrauer, OT Wolf… - Brain Structure and …, 2024 - Springer
Neural representations are internal brain states that constitute the brain's model of the
external world or some of its features. In the presence of sensory input, a representation may …
external world or some of its features. In the presence of sensory input, a representation may …
Computational models of category-selective brain regions enable high-throughput tests of selectivity
NA Ratan Murty, P Bashivan, A Abate… - Nature …, 2021 - nature.com
Cortical regions apparently selective to faces, places, and bodies have provided important
evidence for domain-specific theories of human cognition, development, and evolution. But …
evidence for domain-specific theories of human cognition, development, and evolution. But …
THINGS: A database of 1,854 object concepts and more than 26,000 naturalistic object images
In recent years, the use of a large number of object concepts and naturalistic object images
has been growing strongly in cognitive neuroscience research. Classical databases of …
has been growing strongly in cognitive neuroscience research. Classical databases of …
Texture-like representation of objects in human visual cortex
AV Jagadeesh, JL Gardner - Proceedings of the National …, 2022 - National Acad Sciences
The human visual ability to recognize objects and scenes is widely thought to rely on
representations in category-selective regions of the visual cortex. These representations …
representations in category-selective regions of the visual cortex. These representations …
Sensitivity to geometric shape regularity in humans and baboons: A putative signature of human singularity
M Sablé-Meyer, J Fagot, S Caparos… - Proceedings of the …, 2021 - National Acad Sciences
Among primates, humans are special in their ability to create and manipulate highly
elaborate structures of language, mathematics, and music. Here we show that this sensitivity …
elaborate structures of language, mathematics, and music. Here we show that this sensitivity …
Toward scalable, efficient, and accurate deep spiking neural networks with backward residual connections, stochastic softmax, and hybridization
Spiking Neural Networks (SNNs) may offer an energy-efficient alternative for implementing
deep learning applications. In recent years, there have been several proposals focused on …
deep learning applications. In recent years, there have been several proposals focused on …
Canonical circuit computations for computer vision
Advanced computer vision mechanisms have been inspired by neuroscientific findings.
However, with the focus on improving benchmark achievements, technical solutions have …
However, with the focus on improving benchmark achievements, technical solutions have …