Automated Architecture Design for Deep Neural Networks

08/22/2019
by   Steven Abreu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/12/2021

Machine learning and deep learning

Today, intelligent systems that offer artificial intelligence capabiliti...
research
06/27/2023

Homological Neural Networks: A Sparse Architecture for Multivariate Complexity

The rapid progress of Artificial Intelligence research came with the dev...
research
12/02/2016

Cognitive Deep Machine Can Train Itself

Machine learning is making substantial progress in diverse applications....
research
09/17/2019

Ludwig: a type-based declarative deep learning toolbox

In this work we present Ludwig, a flexible, extensible and easy to use t...
research
07/30/2018

Faster Convergence & Generalization in DNNs

Deep neural networks have gained tremendous popularity in last few years...
research
01/30/2018

Structured Memory based Deep Model to Detect as well as Characterize Novel Inputs

While deep learning has pushed the boundaries in various machine learnin...
research
12/14/2020

Graphs for deep learning representations

In recent years, Deep Learning methods have achieved state of the art pe...

Please sign up or login with your details

Forgot password? Click here to reset