TY - JOUR AU - Hryniowski, Andrew AU - Wong, Alexander PY - 2020/01/02 Y2 - 2024/03/28 TI - DeepLABNet: End-to-end Learning of Deep Radial Basis Networks JF - Journal of Computational Vision and Imaging Systems JA - J. Comp. Vis. Imag. Sys. VL - 5 IS - 1 SE - Articles DO - UR - https://openjournals.uwaterloo.ca/index.php/vsl/article/view/1663 SP - 1 AB - <p>Radial basis function (RBF) networks provide an interesting mechanism for learning complex non-linear activation functions in a neural<br>network. However, the interest in RBF networks has waned due<br>to the difficulty of integrating RBFs into deep neural network architectures in a tractable and stable manner. In this work, we present<br>a novel approach that enables end-to-end learning of deep RBF<br>networks with fully learnable activation basis functions in a tractable<br>manner. We demonstrate that our approach for enabling the use of<br>learnable activation basis functions in deep neural networks, which<br>we will refer to as DeepLABNet, is an effective tool for automated<br>activation function learning within complex network architectures.</p> ER -