Receptive fields of single neurones in the cat's striate cortex

By David H. Hubel, T. Wiesel. 1959

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

BAM: Bottleneck Attention Module (2018, background): “BAM then gradually focuses on the exact target which is a high-level semantic.”
Deep learning in neural networks: An overview (2014, background): “2 Around 1960: Visual Cortex Provides Inspiration for DL Simple cells and complex cells were found in the cat’s visual cortex (e.g., Hubel and Wiesel, 1962; Wiesel and Hubel, 1959).”
High-Performance Neural Networks for Visual Object Classification (2011, background): “CNNs are hierarchical neural networks whose convolutional layers alternate with subsampling layers, reminiscent of simple and complex cells in the primary visual cortex (Wiesel and Hubel, 1959).”
Breast Cancer Multi-classification from Histopathological Images with Structured Deep Learning Model (2017, methodology): “Furthermore, although CNNs inspired by Kunihiko Fukushima 26, 27 , has been used for medical image analysis, e.g., image segmentation 28, 29 image fusion and registration 30–32 , but there still exists a lot of room for improvement of medical data in comparison with the computer vision domain 7, 33–”
Multi-column deep neural networks for image classification (2012, methodology): “The approach is inspired by Hubel and Wiesel’s seminal work on the cat’s primary visual cortex [40], which identified orientation-selective simple cells with overlapping local receptive fields and complex cells performing down-sampling-like operations [15].”
Multiclass Object Recognition with Sparse, Localized Features (2006, background): “All start with an image layer of grayscale pixels and successively compute higher layers, alternating " S " and " C " layers (named by analogy with the V1 simple and complex cells discovered by Hubel and Wiesel [13]).”
Deep convolutional models improve predictions of macaque V1 responses to natural images (2017, background): “Primary visual 3 cortex (V1) has been a strong focus of sensory neuroscience ever since Hubel and 4 Wiesel’s seminal studies demonstrated that neurons in primary visual cortex (V1) 5 respond selectively to distinct image features like local orientation and contrast [2, 3].”
Attractor and integrator networks in the brain (2021, methodology): “…key properties of ring attractor networks [ 17 ] : V1 and V2 cells exhibit strong orientation-tuned responses to real and illusory edges in the visual world [ 226, 227, 228 ] , and population-wide V1 spontaneous activity during sleep is correlated with these tuned population coding states [ 229 ] .”
A survey of the recent architectures of deep convolutional neural networks (2019, methodology): “CNN history begins with the neurobiological experiments conducted by Hubel and Wiesel (1959, 1962) (Hubel and Wiesel 1959, 1962).”
On layer-wise representations in deep neural networks (2013, background): “For example, studies by Hubel and Wiesel (1959), Serre et al. (2005), Wibisono et al. (2010) provide compelling evidence that deep processing also takes place in the brain.”
Representation Learning: A Review and New Perspectives (2012, background): “Based on such structure, one can define local receptive fields (Hubel and Wiesel, 1959), so that each lowlevel feature will be computed from only a subset of the input: a neighborhood in the topology (e.g. a sub-image at a given position).”
Max-pooling convolutional neural networks for vision-based hand gesture recognition (2011, background): “tures, following Hubel and Wiesel’s classic 1962 work on the cat’s primary visual cortex [26], which identified orientationselective simple cells with local receptive fields similar to those of convolutional layers, and complex cells performing subsampling-like operations [27].”