A First Step Toward Incremental Evolution of Convolutional Neural Networks
A First Step Toward Incremental Evolution of Convolutional Neural Networks
复制标题
卷积神经网络增量进化的第一步
DOI:
10.1145/3377929.3389916
复制
发表时间:
2020
期刊:
影响因子:
--
通讯作者:
Louis, Sushil
中科院分区:
文献类型:
--
作者:
Barnes, Dustin;Davis, Sara R;Hand, Emily M;Louis, Sushil
We introduce a novel algorithm - ConvNEAT - that evolves a convolutional neural network (CNN) from a minimal architecture. Convolutional and dense nodes are evolved without restriction to the number of nodes or connections between nodes. The proposed work advances the field with ConvNEAT's ability to evolve arbitrary minimal architectures with multi-dimensional inputs using GPU processing.