paper-with-me

Papers

Finding Better Topologies for Deep Convolutional Neural Networks by Evolution

2018-09-10 · Honglei Zhang, Serkan Kiranyaz, Moncef Gabbouj

Due to the nonlinearity of artificial neural networks, designing topologies for deep convolutional neural networks (CNN) is a challenging task and often only heuristic approach, such as trial and error, can be applied. An evolutionary algorithm can solve optimization problems where the fitness landscape is unknown. However, evolutionary algorithms are computing resource intensive, which makes it difficult for problems when deep CNNs are involved. In this paper, we propose an evolutionary strategy to find better topologies for deep CNNs. Incorporating the concept of knowledge inheritance and knowledge learning, our evolutionary algorithm can be executed with limited computing resources. We applied the proposed algorithm in finding effective topologies of deep CNNs for the image classification task using CIFAR-10 dataset. After the evolution, we analyzed the topologies that performed well for this task. Our studies verify the techniques that have been commonly used in human designed deep CNNs. We also discovered that some of the graph properties greatly affect the system performance. We applied the guidelines learned from the evolution and designed new network topologies that outperform Residual Net with less layers on CIFAR-10, CIFAR-100, and SVHN dataset.

📄 PDF Abstract BibTeX arXiv:1809.03242

Code (0)

등록된 구현이 없습니다.

Tasks

Evolutionary Algorithmsimage-classificationImage Classification

Similar Papers 제목 키워드 기반

An Artificial Neural Network Functionalized by Evolution

2022-05-16 · Fabien Furfaro, Avner Bar-Hen, Geoffroy Berthelot

The topology of artificial neural networks has a significant effect on their performance. Characterizing efficient topology is a field of promising research in Artificial Intelligence. However, it is not a trivial task a…

Artificial Life

Combining Neuro-Evolution of Augmenting Topologies with Convolutional Neural Networks

2022-10-20 · Jan Hohenheim, Mathias Fischler, Sara Zarubica, Jeremy Stucki

Current deep convolutional networks are fixed in their topology. We explore the possibilites of making the convolutional topology a parameter itself by combining NeuroEvolution of Augmenting Topologies (NEAT) with Convol…

Large Scale Evolution of Convolutional Neural Networks Using Volunteer Computing

2017-03-15 · Travis Desell

This work presents a new algorithm called evolutionary exploration of augmenting convolutional topologies (EXACT), which is capable of evolving the structure of convolutional neural networks (CNNs). EXACT is in part mode…

Distributed ComputingL2 Regularization

Accelerating the Evolution of Convolutional Neural Networks with Node-Level Mutations and Epigenetic Weight Initialization

2018-11-17 · Travis Desell

This paper examines three generic strategies for improving the performance of neuro-evolution techniques aimed at evolving convolutional neural networks (CNNs). These were implemented as part of the Evolutionary eXplorat…

Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control

2019-10-28 · Jörg K. H. Franke, Gregor Köhler, Noor Awad, Frank Hutter

Current Deep Reinforcement Learning algorithms still heavily rely on handcrafted neural network architectures. We propose a novel approach to automatically find strong topologies for continuous control tasks while only a…

continuous-controlContinuous ControlDeep Reinforcement Learningreinforcement-learning+2