DeepLABNet: End-to-end Learning of Deep Radial Basis Networks

Abstract

Radial basis function (RBF) networks provide an interesting mechanism for learning complex non-linear activation functions in a neural
network. However, the interest in RBF networks has waned due
to the difficulty of integrating RBFs into deep neural network architectures in a tractable and stable manner. In this work, we present
a novel approach that enables end-to-end learning of deep RBF
networks with fully learnable activation basis functions in a tractable
manner. We demonstrate that our approach for enabling the use of
learnable activation basis functions in deep neural networks, which
we will refer to as DeepLABNet, is an effective tool for automated
activation function learning within complex network architectures.