Unsupervised Spatial-Spectral Network Learning for Hyperspectral Compressive Snapshot Reconstruction

Information plane analysis, describing the mutual information between the input and a hidden layer and between a hidden layer and the target over time, has recently been proposed to analyze the training of neural networks. Since the activations of a hidden layer are typically continuous-valued, this mutual information cannot be computed analytically and must thus be estimated, resulting in apparently inconsistent or even contradicting results in the literature. The goal of this paper is to demonstrate how information plane analysis can still be a valuable tool for analyzing neural network training. To this end, we complement the prevailing binning estimator for mutual information with a geometric interpretation. With this geometric interpretation in mind, we evaluate the impact of regularization and interpret phenomena such as underfitting and overfitting. In addition, we investigate neural network learning in the presence of noisy data and noisy labels.

Download Full-text

Innovative Applications Mode of Network Learning Space in Exercise Physiology Based on Ubiquitous Learning

International Journal of Emerging Technologies in Learning (iJET) ◽

10.3991/ijet.v14i04.10117 ◽

2019 ◽

Vol 14 (04) ◽

pp. 113 ◽

Cited By ~ 3

Author(s):

Jie Kong

Keyword(s):

Flipped Classroom ◽

Exercise Physiology ◽

Internet Technology ◽

Traditional Teaching ◽

Ubiquitous Learning ◽

Learning Space ◽

Network Teaching ◽

Network Learning ◽

Space Construction

With continuous development of internet technology, the concept of ubiquitous learning and network learning space have received more and more attention from scholars, and gradually become the research focuses. College classroom has turned to network teaching from traditional teaching. In this study, literature review and case study were combined with ubiquitous learning and network learning space construction to systematically discuss classification and concept models of network learning space under the perspective of ubiquitous learning. Meanwhile, four models based on network learning space were proposed, and flipped classroom network teaching model was applied in the course of Exercise Physiology. The study showed that, the model has the good teaching effect in course teaching. It not just improves students’ interest, but also lays a foundation for popularizing the teaching mode.

Download Full-text

Hybrid PSO-black stork foraging for functional neural fuzzy network learning enhancement

2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC) ◽

10.1109/icsmc.2012.6377919 ◽

2012 ◽

Author(s):

Zakaria A. Hamed ◽

S. Z. Mohd Hashim

Keyword(s):

Learning Enhancement ◽

Network Learning ◽

Black Stork ◽

Fuzzy Network ◽

Neural Fuzzy Network ◽

Neural Fuzzy

Download Full-text

Study on the Operation Model of Colleges Network Learning Propaganda and Public Opinion Guidance Based on the Internet

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.380-384.2104 ◽

2013 ◽

Vol 380-384 ◽

pp. 2104-2108

Author(s):

Chen Liang Li ◽

Ming Xia Zhu

Keyword(s):

Public Opinion ◽

Information Science ◽

Internet Technology ◽

The Internet ◽

C Language ◽

Network Learning ◽

Maximum Value ◽

Network Transmission ◽

The Impact ◽

Important Significance

With the development of computer information science and technology, Internet has a large number of network propaganda and public opinion page every day. Through the network micro message and the micro-blog forwarding, network propaganda and public opinion have the impact on the development and stability of colleges, so the study network propaganda and public opinion has important significance for the development of colleges. Under this background, based on the computer Internet technology, the Internet erection of network propaganda guidance mode are analyzed, and compared with the fuzzy minimum production tree theory and the C language software, the network construction is verified. Finally the iterative process of finding the network transmission is relatively stable, after 800 iterative steps, numerical is slowly increasing, in which the maximum value is about 0.0001. The seven school propaganda is been as the minimum spanning of tree main network, its sum of weighted has been up to 1606.

Download Full-text