A General Approach to State Refinement
Gerard Kennedy,Jin Gao,Zheyu Zhuang,Xin Yu,Robert Mahony,Gerard Kennedy,Jin Gao,Zheyu Zhuang,Xin Yu,Robert Mahony
Deep learning algorithms such as Convolutional Neural Networks (CNNs) are currently used to solve a range of robotics and computer vision problems. These networks typically estimate the desired representation in a single forward pass and must therefore learn to converge from a wide range of initial conditions to a precise result. This is challenging, and has led to increased interest in the develo...
