Figure - available via license: CC BY
Content may be subject to copyright.
Source publication
Convolutional neural networks have powerful performances in many visual tasks because of their hierarchical structures and powerful feature extraction capabilities. SPD (symmetric positive definition) matrix is paid attention to in visual classification, because it has excellent ability to learn proper statistical representation and distinguish sam...
Context in source publication
Context 1
... gain of the SPD matrix network trained by SPD matrices based on pool2 convolution features of VGG19 relative to GoogLeNet is about 0.6 dB when the detection probability of both models reaches 70%, and the gain of the SPD matrix network trained by SPD matrices based on the convolution features of GoogLeNetV3 relative to GoogLeNet is 2 dB when the detection probability of both models reaches 80%. Table 1 is the comparision of the false alarm probability about different models involved in this paper. The false alarm probability of them is not greater than 10 under the circumstance of the SCR is −5 dB. ...Similar publications
Machine-learning techniques achieve excellent performance in modern applications. In particular, neural networks enable training classifiers, often used in safety-critical applications, to complete a variety of tasks without human supervision. Neural-network models have neither the means to identify what they do not know nor to interact with the hu...
