Toward reflective spiking neural networks exploiting memristive devices
The design of modern convolutional artificial neural networks (ANNs) composed of formal
neurons copies the architecture of the visual cortex. Signals proceed through a hierarchy …
neurons copies the architecture of the visual cortex. Signals proceed through a hierarchy …
A survey of the recent architectures of deep convolutional neural networks
Abstract Deep Convolutional Neural Network (CNN) is a special type of Neural Networks,
which has shown exemplary performance on several competitions related to Computer …
which has shown exemplary performance on several competitions related to Computer …
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by
learning increasingly complex representations of object shapes. Some recent studies …
learning increasingly complex representations of object shapes. Some recent studies …
Normalization and pooling in hierarchical models of natural images
LG Sanchez-Giraldo, MNU Laskar… - Current opinion in …, 2019 - Elsevier
Highlights•Subunit pooling and normalization are building blocks of hierarchical cortical
models.•Image statistics models predict when normalization is recruited in primary …
models.•Image statistics models predict when normalization is recruited in primary …
Neural echos: Depthwise convolutional filters replicate biological receptive fields
In this study, we present evidence suggesting that depthwise convolutional kernels are
effectively replicating the structural intricacies of the biological receptive fields observed in …
effectively replicating the structural intricacies of the biological receptive fields observed in …
Multi-scale hierarchical neural network models that bridge from single neurons in the primate primary visual cortex to object recognition behavior
Object recognition relies on inferior temporal (IT) cortical neural population representations
that are themselves computed by a hierarchical network of feedforward and recurrently …
that are themselves computed by a hierarchical network of feedforward and recurrently …
Bioacoustic classification of antillean manatee vocalization spectrograms using deep convolutional neural networks
We evaluated the potential of using convolutional neural networks in classifying
spectrograms of Antillean manatee (Trichechus manatus manatus) vocalizations …
spectrograms of Antillean manatee (Trichechus manatus manatus) vocalizations …
Multi-Scale Convolutional Neural Network for Temporal Knowledge Graph Completion
W Liu, P Wang, Z Zhang, Q Liu - Cognitive Computation, 2023 - Springer
Abstract Knowledge graph completion is a critical task in natural language processing. The
task becomes more challenging on temporal knowledge graph, where each fact is …
task becomes more challenging on temporal knowledge graph, where each fact is …
Integrating flexible normalization into midlevel representations of deep convolutional neural networks
LGS Giraldo, O Schwartz - Neural computation, 2019 - direct.mit.edu
Deep convolutional neural networks (CNNs) are becoming increasingly popular models to
predict neural responses in visual cortex. However, contextual effects, which are prevalent in …
predict neural responses in visual cortex. However, contextual effects, which are prevalent in …
A neurobiological evaluation metric for neural network model search
N Blanchard, J Kinnison… - Proceedings of the …, 2019 - openaccess.thecvf.com
Neuroscience theory posits that the brain's visual system coarsely identifies broad object
categories via neural activation patterns, with similar objects producing similar neural …
categories via neural activation patterns, with similar objects producing similar neural …