scholarly journals A self-organizing neural network model of receptive field and map development of motion direction selectivity, orientation, and ocular dominance in V1 and MT

2004 ◽  
Vol 4 (8) ◽  
pp. 280-280
Author(s):  
A. M. Harner ◽  
T. Watanabe
2021 ◽  
Vol 292 ◽  
pp. 116912
Author(s):  
Rong Wang Ng ◽  
Kasim Mumtaj Begam ◽  
Rajprasad Kumar Rajkumar ◽  
Yee Wan Wong ◽  
Lee Wai Chong

Author(s):  
Kun Xu ◽  
Shunming Li ◽  
Jinrui Wang ◽  
Zenghui An ◽  
Yu Xin

Deep learning method is gradually applied in the field of mechanical equipment fault diagnosis because it can learn complex and useful features automatically from the vibration signals. Among the many intelligent diagnostic models, convolutional neural network has been gradually applied to intelligent fault diagnosis of bearings due to its advantages of local connection and weight sharing. However, there are still some drawbacks. (1) The training process of convolutional neural network is slow and unstable. It has more training parameters. (2) It cannot perform well under different working conditions, such as noisy environment and different workloads. In this paper, a novel model named adaptive and fast convolutional neural network with wide receptive field is presented to overcome the aforementioned deficiencies. The prime innovations include the following. First, a deep convolutional neural network architecture is constructed using the scaled exponential linear unit activation function and global average pooling. The model has fewer training parameters and can converge rapidly and stably. Second, the model has a wide receptive field with two medium and three small length convolutional kernels. It also has high diagnostic accuracy and robustness when the environment is noisy and workloads are changed compared with other models. Furthermore, to demonstrate how the wide receptive field convolutional neural network model works, the reasons for high model performance are analyzed and the learned features are also visualized. Finally, the wide receptive field convolutional neural network model is verified by the vibration dataset collected in the background of high noise, and the results indicate that it has high diagnostic performance.


2000 ◽  
Vol 14 (17) ◽  
pp. 1815-1824
Author(s):  
M. ANDRECUT ◽  
M. K. ALI

We describe a new biologically motivated model of the sensory-motor mechanism. The model is based on a self-organizing neural network with modifiable lateral interactions and a "master-slave" connection between the sensorial and motor modules. The results show that the described model is a useful feature that can be exploited by autonomous agents. An example of implementation in the case of a "moving virtual creature" is also presented.


2014 ◽  
Vol 140 (2) ◽  
pp. 05014001 ◽  
Author(s):  
Yang Gao ◽  
Zhe Feng ◽  
Yang Wang ◽  
Jin-Long Liu ◽  
Shuang-Cheng Li ◽  
...  

2000 ◽  
Vol 73 (9) ◽  
pp. 1955-1965 ◽  
Author(s):  
Hiroko Satoh ◽  
Kimito Funatsu ◽  
Keiko Takano ◽  
Tadashi Nakata

1991 ◽  
Vol 27 (Supplement) ◽  
pp. 114-115
Author(s):  
Shigekazu Ishihara ◽  
Keiko Hatamoto ◽  
Mitsuo Nagamachi ◽  
Yukihiro Matsubara

Sign in / Sign up

Export Citation Format

Share Document