Search

In steerable filters, a filter of arbitrary orientation can be generated by a linear combination of a set of “basis filters.” Steerable properties dominate the design of the traditional filters, e.g., Gabor filters and endow features the capability of handling spatial transformations. However, such properties have not yet been well explored in the deep convolutional neural networks (DCNNs). In this paper, we develop a new deep model, namely, Gabor convolutional networks (GCNs or Gabor CNNs), with Gabor filters incorporated into DCNNs such that the robustness of learned features against the orientation and scale changes can be reinforced. By manipulating the basic element of DCNNs, i.e., the convolution operator, based on Gabor filters, GCNs can be easily implemented and are readily compatible with any popular deep learning architecture. We carry out extensive experiments to demonstrate the promising performance of our GCNs framework, and the results show its superiority in recognizing objects, especially when the scale and rotation changes take place frequently. Moreover, the proposed GCNs have much fewer network parameters to be learned and can effectively reduce the training complexity of the network, leading to a more compact deep learning model while still maintaining a high feature representation capacity. The source code can be found at https://github.com/bczhangbczhang. [ABSTRACT FROM AUTHOR]

In this paper, a Takagi—Sugeno—Kang-type fuzzy-neural-network control (T-FNNC) scheme is constructed for an n-link robot manipulator to achieve high-precision position tracking. According to the concepts of mechanical geometry and motion dynamics, the dynamic model of an n-link robot manipulator including actuator dynamics is introduced initially. However, it is difficult to design a suitable model-based control scheme due to the uncertainties in practical applications, such as friction forces, external disturbances and parameter variations. In order to cope with this problem, a T-FNNC system without the requirement of prior system information and auxiliary control design is investigated to the joint position control of an n-link robot manipulator for periodic motion. In this model-free control scheme, a five-layer fuzzy-neural-network is utilized for the major control role, and the adaptive tuning laws of network parameters are established in the sense of projection algorithm and Lyapunov stability theorem to ensure the network convergence as well as stable control performance. In addition, experimental results of a two-link robot manipulator actuated by dc servomotors are provided to verify the effectiveness and robustness of the proposed T-FNNC methodology. [ABSTRACT FROM AUTHOR]