Performance-optimized hierarchical models predict neural responses in higher visual cortex
The ventral visual stream underlies key human visual object recognition abilities. However,
neural encoding in the higher areas of the ventral stream remains poorly understood. Here …
neural encoding in the higher areas of the ventral stream remains poorly understood. Here …
Deep neural networks reveal a gradient in the complexity of neural representations across the ventral stream
U Güçlü, MAJ Van Gerven - Journal of Neuroscience, 2015 - Soc Neuroscience
Converging evidence suggests that the primate ventral visual pathway encodes increasingly
complex stimulus features in downstream areas. We quantitatively show that there indeed …
complex stimulus features in downstream areas. We quantitatively show that there indeed …
Deep neural networks rival the representation of primate IT cortex for core visual object recognition
The primate visual system achieves remarkable visual object recognition performance even
in brief presentations, and under changes to object exemplar, geometric transformations …
in brief presentations, and under changes to object exemplar, geometric transformations …
Simple learned weighted sums of inferior temporal neuronal firing rates accurately predict human core object recognition performance
To go beyond qualitative models of the biological substrate of object recognition, we ask:
can a single ventral stream neuronal linking hypothesis quantitatively account for core object …
can a single ventral stream neuronal linking hypothesis quantitatively account for core object …
[图书][B] Visual cortex and deep networks: learning invariant representations
A mathematical framework that describes learning of invariant representations in the ventral
stream, offering both theoretical development and applications. The ventral visual stream is …
stream, offering both theoretical development and applications. The ventral visual stream is …
Recurrence is required to capture the representational dynamics of the human visual system
TC Kietzmann, CJ Spoerer… - Proceedings of the …, 2019 - National Acad Sciences
The human visual system is an intricate network of brain regions that enables us to
recognize the world around us. Despite its abundant lateral and feedback connections …
recognize the world around us. Despite its abundant lateral and feedback connections …
Deep supervised, but not unsupervised, models may explain IT cortical representation
SM Khaligh-Razavi, N Kriegeskorte - PLoS computational biology, 2014 - journals.plos.org
Inferior temporal (IT) cortex in human and nonhuman primates serves visual object
recognition. Computational object-vision models, although continually improving, do not yet …
recognition. Computational object-vision models, although continually improving, do not yet …
Hierarchical modular optimization of convolutional networks achieves representations similar to macaque IT and human ventral stream
Humans recognize visually-presented objects rapidly and accurately. To understand this
ability, we seek to construct models of the ventral stream, the series of cortical areas thought …
ability, we seek to construct models of the ventral stream, the series of cortical areas thought …
Unsupervised neural network models of the ventral visual stream
Deep neural networks currently provide the best quantitative models of the response
patterns of neurons throughout the primate ventral visual stream. However, such networks …
patterns of neurons throughout the primate ventral visual stream. However, such networks …
Brain-like object recognition with high-performing shallow recurrent ANNs
Deep convolutional artificial neural networks (ANNs) are the leading class of candidate
models of the mechanisms of visual processing in the primate ventral stream. While initially …
models of the mechanisms of visual processing in the primate ventral stream. While initially …