21 April 2021 in ASP Transactions on Pattern Recognition and Intelligent Systems
The Principle of Homology Continuity (PHC) based covering learning method is an effective method to solve the pattern recognition problem. However, PHC and the existence of optimal coverage are not mathematical proven. To address this issue, we firstly give the mathematical description and theoretical proof of PHC. On this basis, the theoretical definition of optimal coverage is introduced. Optimal coverage can determine the internal connections among samples as prior knowledge and use covering neurons to learn prior knowledge. Finally, we propose a kind of covering neuron model, and the effectiveness of which is demonstrated through extensive experiments conducted on the CIFAR-10, LFW, and YTF datasets.
23 March 2020 in IEEE Access
In order to improve the accuracy of capsule network in disentangled representation, and further expand its application in computer vision, a novel BDARS_CapsNet (bi-directional attention routing sausage capsule network) architecture is proposed in this paper. Firstly, the bi-directional routing, namely bottom-up and top-down attention is used to achieve information feed-forward and feedback mechanism, which contributes to describing the attributes of object entity more accurately and completely. Secondly, inspired by the concept of covering learning, the sausage measure model is introduced into the network. The sausage model measures both the similarities and differences of the capsules and projects them into a more complex curved surface, which makes it possible to approximate any nonlinear function with arbitrary precision and preserving the local responsiveness of capsule entity to the maximum. Finally, the BDARS_CapsNet combines the CNN (Convolutional Neural Network), bi-directional attention routing, and sausage measure into capsule network modeling, and makes full use of high-level category information and low-level vision information; as a result, the reconstruction and classification accuracy is accordingly improved. Experiments demonstrate the effectiveness of proposed information routing, sausage measure, and new framework. Furthermore, the proposed BDARS_CapsNet provides a foundation for future research on disentangled representation learning.