Receptive fields and functional architecture of monkey striate cortex

By David H. Hubel, T. Wiesel. 1968

How researchers see this paper

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

In Evaluation & Benchmarks

Citations in the corpus

Learning Convolutional Neural Networks for Graphs (2016, background): “Each graph can be represented by an adjacency matrix A of size n × n , where A i,j = 1 if there is an edge from vertex v i to vertex v j , and A i,j = 0 otherwise.”
Recent advances in convolutional neural networks (2015, background): “In 1959, Hubel & Wiesel [1] found that cells in animal visual cortex are responsible for detecting light in receptive ﬁelds.”
Scaling Local Self-Attention for Parameter Efficient Visual Backbones (2021, background): “To deal with the computational cost in larger resolutions where global attention is infeasible, we follow the fairly general principle of local processing, which is at the heart of convolutions and natural perceptual systems [22, 23], and use spatially restricted forms of self-attention.”
Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks (2013, background): “A pooling operator, an idea which dates back to the work in [17], has been adopted in many object recognizers.”
On Invariance and Selectivity in Representation Learning (2015, methodology): “In this work, we develop an ML perspective closely following computational neuroscience models of the information processing in the visual cortex [21,22,33].”
Remote Sensing Image Fusion Based on Two-Stream Fusion Network (2017, methodology): “The design of CNN was inspired by the organization of visual cortex in mammal animals that individual cortical neuron only responds to a sub-region of visual field, called receptive field, and neighboring neurons share similar even overlap receptive fields [36].”
A review on deep convolutional neural networks (2017, methodology): “INTRODUCTION onvolutional Neural Network is the widely used deep learning framework [1] which was inspired by the visual cortex of animals [2].”
Building the gist of a scene: the role of global image features in recognition. (2006, background): “This suggests that a reliable scene representation can be built, in a feed-forward manner, from the same low-level features used for local neural representations of an image (receptive fields of early visual areas, Hubel and Wiesel, 1968 ).”
Invariant Visual Object and Face Recognition: Neural and Computational Bases, and a Model, VisNet (2012, unknown): “This approach received neurophysiological support early on from the results of Hubel and Wiesel (1962) and Hubel and Wiesel (1968) in the cat and monkey, and many of the data described in Chapter 5 of Rolls and Deco (2002) are consistent with this scheme.”
Deep learning in bioinformatics (2016, unknown): “In the visual cortex, there is a hierarchy of two basic cell types: simple cells and complex cells [69].”
Structure and function of visual area MT. (2005, background): “In the primate, visual motion is first computed in V1, and these neurons have small receptive fields; therefore, investigators generally think that V1 neurons see normal (orthogonal) velocities (Hubel & Wiesel 1968, Movshon et al. 1985, Heeger 1987).”
Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction (2011, background): “CNNs are hierarchical models whose convolutional layers alternate with subsampling layers, reminiscent of simple and complex cells in the primary visual cortex [11].”
Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs (2018, background): “For example, SIFT features are local features descriptors constructed such that they are invariant to translation, scaling and rotation Lowe (1999). In addition, by using blurring, SIFT features become somewhat robust to deformations.”