EnergyNet: Energy-based Adaptive Structural Learning of Artificial Neural Network Architectures

TL;DR

EnergyNet is a novel framework that adaptively learns neural network structures using energy functions, providing unsupervised, theoretically grounded architecture optimization that adapts to problem complexity.

Contribution

It introduces an energy-based adaptive structural learning method for neural networks, grounded in RBM energy guarantees, with experimental validation.

Findings

Network structures adapt to problem complexity.

Unsupervised learning of architectures.

Theoretical guarantees based on RBM energy functions.

Abstract

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.