Receptive fields.

By P. Lennie. 2003

316 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Molecular Biology

How researchers see this paper

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

In Cognitive Neuroscience

In Molecular Biology

Citations in the corpus

A self-organizing neural network architecture for learning human-object interactions (2017, background): “Neuroscientists have widely studied object and action perception, with a focus on where and how the visual cortex constructs invariant object representations [8] and”
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].”
Selective Kernel Networks (2019, methodology): “The Classical RFs (CRFs) of neurons in the V1 region was discovered by Hubel and Wiesel [14], as determined by single oriented bars.”
Recurrent convolutional neural network for object recognition (2015, methodology): “Inspired by Rubel and Wiesel's breakthrough findings in cat [23][22], Fukushima [13] proposed a hierarchical model called Neocognitron, which consisted of stacked pairs of simple unit layer and complex unit layer.”
Electronic Nose and Its Applications: A Survey (2019, unknown): “Specifically, convolutional neural networks (CNNs)[109] proposed by Hubel and Wiesel in 1962[110], have been frequently used among other deep learning techniques.”
Unsupervised learning of invariant representations (2016, background): “Consider an HW-module of “simple” and “complex” cells [1] looking at the image through a window defined by their receptive fields.”
Are sparse representations really relevant for image classification? (2011, background): “The choice of having a pooling stage is based on two relevant aspects: • From a biological perspective, the pooling stage corresponds to the complex cells’ layers in Hubel and Wiesel’s model of V1 cortex [10].”
Computational analysis and learning for a biologically motivated model of boundary detection (2008, methodology): “This has resulted in efficient algorithms for problems like edge detection [9,15,54,64], image denoising [18,65] and segmentation [56,60] on the one hand and an increasingly detailed understanding of the functions of neurons in the first stages of the visual cortex on the other [37,38,78].”
Ultra-Fast MRI of the Human Brain with Simultaneous Multi-Slice Imaging (2013, background): “cortical columns [7] have been identified with functional MRI (fMRI) [8].”
Transfer learning using computational intelligence: A survey (2015, background): “Likewise, based on the multi-stage Hubel-Wiesel architectures, whether shared hidden layers trained by the source task can be reused on a different target task is detected.”
A survey of deep neural network architectures and their applications (2017, background): “In the 1960s, Hubel and Wisel [73] proposed a concept called receptive fields.”
Automatic Feature Learning for Robust Shadow Detection (2014, methodology): “ConvNets are biologically inspired deep network architectures based on Hubel and Wiesel’s [11] work on the cat’s primary visual cortex.”
Building high-level features using large scale unsupervised learning (2011, background): “These properties in turn were characterized by [11, 12].”
Learning in the Machine: Random Backpropagation and the Deep Learning Channel (2016, methodology): “Note that Hebbian learning [15] is a form of local learning, and deep local learning has been proposed for instance by Fukushima [10] to train the neocognitron architecture, essentially a feed forward convolutional neural network inspired by the earlier neurophysiological work of Hubel and Wiesel [1”