China 
Africa 
Explore chapters and articles related to this topic
Introduction
Published in Limiao Deng, Cognitive and Neural Modelling for Visual Information Representation and Memorization, 2022
The convolutional and pooling layers in ConvNets are directly inspired by the classic notions of simple cells and complex cells in visual neuroscience38, and the overall architecture is reminiscent of the LGN–V1–V2–V4–IT hierarchy in the visual cortex ventral pathway39. When ConvNet models and monkeys are shown the same picture, the activations of high-level units in the ConvNet explain half of the variance of random sets of 160 neurons in the monkey's inferotemporal cortex40. ConvNets have their roots in the neocognitron41, the architecture of which was somewhat similar but did not have an end-to-end supervised-learning algorithm such as backpropagation. A primitive 1D ConvNet called a time-delay neural net was used for the recognition of phonemes and simple words42,43.
An Unexpected Renaissance Age
Published in Alessio Plebe, Pietro Perconti, The Future of the Artificial Mind, 2021
Alessio Plebe, Pietro Perconti
Nevertheless, this impetus of studies on the analogies between DCNN and the visual system has had the benefit of intriguing the visual neuroscience community with regard to DCNN models, thus bringing neuroscience closer to AI. The reactions on the neuroscientific side are varied, and span from positive acceptance (Gauthier and Tarr, 2016; VanRullen, 2017), to a cautious interest (Lehky and Tanaka, 2016; Grill-Spector et al., 2018; Tacchetti et al., 2018), down to more skeptical stances (Olshausen, 2014; Robinson and Rolls, 2015; Rolls, 2016; Conway, 2018).
Optical fiber communication and sensitivity
Published in Muhammad Arif, Guojun Wang, Mazin Abed Mohammed, Md Tabrez Nafis, Vehicular Ad Hoc Networks, 2023
Salma Masuda Binta, Mohammed Hossam-E Haider, Mohammad Farhan Ferdous
In visual neuroscience, spectral sensitivity is used to describe the different characteristics of the photopigments in the rod cells and cone cells in the retina of the eye. It is known that the rod cells are more suited to scotopic vision and cone cells to photopic vision and that they differ in their sensitivity to different wavelengths of light. It has been established that the maximum spectral sensitivity of the human eye under daylight conditions is at a wavelength of 555 nm, while at night the peak shifts to 507 nm.
A strain gauge based locomotion mode recognition method using convolutional neural network
Published in Advanced Robotics, 2019
Yanggang Feng, Wanwen Chen, Qining Wang
A typical CNN architecture is inspired by visual neuroscience [18] and has convolutional layers and pooling layers at its first few stages. Fully connected layers are used after all the convolutional layers and pooling layers. After several stages of convolution and pooling, higher level features are extracted and fed into fully connected layers to output a vector whose dimension is the same as the number of classes. An example of CNN architecture is shown in Figure 2.