The choice of transfer functions may strongly influence complexity and performance of neural networks used in classification and approximation tasks. A taxonomy of activation an...
: A system for learning the pre-grasp positioning task for a robot manipulator is presented. The images delivered from a gripper mounted camera are analysed using Gabor filters wh...
MLUTs used in color characterization require significant memory for embedded systems. Most tools that create device characterization maps, use MLUTs. For this reason, there is int...
—This paper describes a method of linearizing the nonlinear characteristics of many sensors using an embedded neural network. The proposed method allows for complex neural networ...
In this paper, an optimized approximation algorithm (OAA) is proposed to address the overfitting problem in function approximation using neural networks (NNs). The optimized approx...