Neural networks and neuroscience-inspired computer vision.

By David D. Cox, Thomas L. Dean. 2014

228 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biophysics, Electrical and Electronic Engineering

How researchers see this paper

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

In Artificial Intelligence

In Biophysics

In Electrical and Electronic Engineering

Citations in the corpus

The limits and potentials of deep learning for robotics (2018, background): “While there are numerous ﬂaws lurking in the shadows of deep learning benchmarks [12], [22], [80], [115], two key aspects are worth discussing here: 1) the open set nature of decision making in visual recognition problems related to robotics, and 2) the limitations of traditional dataset evaluation…”
On the Origin of Deep Learning (2017, background): “1 Visual Cortex Convolutional Neural Network is widely known as being inspired by visual cortex, however, except that some publications discuss this inspiration briefly (Poggio and Serre, 2013; Cox and Dean, 2014), few resources present this inspiration thoroughly.”
PsyPhy: A Psychophysics Driven Evaluation Framework for Visual Recognition (2016, background): “While certainly capturing some of the operation of the ventral stream (particularly at the ﬁltering stages of early vision), today’s CNN architectures lack the intricate structure and function of biological neural networks [47].”
Survey on semantic segmentation using deep learning techniques (2019, background): “Neural networks have a long history since the 1940s and they did not get much of the attention of researchers until 1990s [1].”
Insects have the capacity for subjective experience (2016, background): “Such theoretical and computational approaches are leading to a better understanding of the cortical neurocytoarchitecture necessary to perform conscious neural processing (Martinet et al., 2011; Cox and Dean, 2014; Huang et al., 2015).”
Towards deep learning with segregated dendrites (2016, background): “Deep learning was motivated by analogies to the real brain (LeCun et al., 2015; Cox and Dean, 2014), so it is tantalizing that recent studies have shown that deep neural networks develop representations that strongly resemble the representations observed in the mammalian neocortex (Khaligh-Razavi an”