Automated Architecture Design for Deep Neural Networks

TL;DR

This paper explores automated methods for designing deep neural network architectures to reduce complexity and improve efficiency, addressing the manual trial-and-error process traditionally used.

Contribution

It introduces novel approaches for automating neural network architecture design, aiming to simplify and optimize the creation of deep learning models.

Findings

Automated design methods can produce less complex neural networks.

Automated approaches achieve competitive performance.

Reduction in manual effort for neural network architecture creation.

Abstract

Machine learning has made tremendous progress in recent years and received large amounts of public attention. Though we are still far from designing a full artificially intelligent agent, machine learning has brought us many applications in which computers solve human learning tasks remarkably well. Much of this progress comes from a recent trend within machine learning, called deep learning. Deep learning models are responsible for many state-of-the-art applications of machine learning. Despite their success, deep learning models are hard to train, very difficult to understand, and often times so complex that training is only possible on very large GPU clusters. Lots of work has been done on enabling neural networks to learn efficiently. However, the design and architecture of such neural networks is often done manually through trial and error and expert knowledge. This thesis inspects different approaches, existing and novel, to automate the design of deep feedforward neural networks in an attempt to create less complex models with good performance that take away the burden of deciding on an architecture and make it more efficient to design and train such deep networks.