Receptive fields, binocular interaction and functional architecture in the cat's visual cortex

By David H. Hubel, T. Wiesel. 1962

How researchers see this paper

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

In Neuroscience

Citations in the corpus

Making Convolutional Networks Shift-Invariant Again (2019, background): “In biological systems, local connectivity was famously discovered in a cat’s visual system (Hubel & Wiesel, 1962).”
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (2021, background): “Its complexity is still quadratic to image size, while ours is linear and also operates locally which has proven beneficial in modeling the high correlation in visual signals [32, 22, 37].”
Dynamic Neural Networks: A Survey (2021, background): “dynamic networks may bridge the gap between the underlying mechanism of deep models and brains, as it is believed that the brains process information in a dynamic way [37], [38].”
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 [37], which identified orientationselective simple cells with overlapping local receptive fields and complex cells performing down-sampling-like operations [15].”
Building high-level features using large scale unsupervised learning (2011, methodology): “In this section, we describe the algorithm that we use to learn features from the unlabeled training set.”
Continual Lifelong Learning with Neural Networks: A Review (2018, background): “The seminal work of Hubel and Wiesel (1967) on the emergence of ocular dominance showed the importance of timing of experience on the development of normal patterns of cortical organization.”
Deep learning in neural networks: An overview (2014, background): “Simple cells and complex cells were found in the cat’s visual cortex (e.g., Hubel & Wiesel, 1962; Wiesel & Hubel, 1959).”
AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation (2018, methodology): “Two popular architectures of neural networks are fully connected feedforward (FNN) and convolutional (CNN).”
Convolution by Evolution: Differentiable Pattern Producing Networks (2016, background): “These architectures were historically inspired by the structure of the mammalian visual system, namely the hierarchical structure of the ventral stream for visual processing [5] and the local, tiled nature of “receptive fields” in the primary visual cortex [10].”
Lifelong learning of human actions with deep neural network self-organization (2017, background): “In fact, a body of literature has suggested that early experiences are particularly influential on human and animal behavior (see e.g. Hubel and Wiesel, 1962, Johnson and Newport, 1991; Senghas, Kita, and Ozyurek, 2004).”
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree (2015, background): “Learning pooling functions is analogous to receptive ﬁeld learning [8, 11, 5, 15].”
From machine learning to machine reasoning (2011, background): “Similar pyramidal structures have long been associated with the visual cortex (Hubel and Wiesel, 1962; Riesenhuber and Poggio, 2003).”
How does the brain solve visual object recognition? (2012, neutral): “This approximates the ‘‘cortical module’’ of Mountcastle (1997) and the ‘‘hypercolumn’’ of Hubel and Wiesel (1974) but is much larger than ‘‘ontogenetic microcolumns’’ suggested by neurodevelopment (Rakic, 1988) and the basic ‘‘canonical cortical circuit’’ (Douglas andMartin, 1991).”
ResNeSt: Split-Attention Networks (2020, background): “The neuron connections in visual cortex have inspired the development of CNNs in the past decades [29].”
Residual Networks are Exponential Ensembles of Relatively Shallow Networks (2016, background): “This formalism is based on the discovery of the receptive ﬁeld [10], which characterizes the visual system as a hierarchical and feedforward system.”