EnergyNet: Energy-based Adaptive Structural Learning of Artificial Neural Network Architectures
This addresses the challenge of manual architecture design for neural networks, though it appears incremental as it builds on existing energy-based methods.
The paper tackles the problem of designing neural network architectures by introducing EnergyNet, a framework that adaptively learns network structures in an unsupervised manner based on energy functions from restricted Boltzmann machines, with experimental results showing the final network adapts to problem complexity.
We present E NERGY N ET , a new framework for analyzing and building artificial neural network architectures. Our approach adaptively learns the structure of the networks in an unsupervised manner. The methodology is based upon the theoretical guarantees of the energy function of restricted Boltzmann machines (RBM) of infinite number of nodes. We present experimental results to show that the final network adapts to the complexity of a given problem.