arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.06629cs.NEcs.LG
收藏

生长型人工神经网络

Growing Artificial Neural Networks

University of Arizona(亚利桑那大学)

John Mixter, Ali Akoglu

摘要:

修剪是减小神经网络大小以适应低SWaP硬件的合理方法,但网络必须离线训练和修剪。我们提出了一种算法,人工神经发生(ANG),增长,而不是修剪的网络,使神经网络进行训练和执行低SWaP嵌入式硬件。ANG通过使用训练数据在实际训练发生之前确定层之间的关键连接来实现这一点。我们的实验使用修改后的LeNet-5作为基线神经网络,使用总共61,160个权重实现了98.74%的测试准确率。ANG生长的网络仅用21,211个权重就实现了98.80%的测试准确率。

英文摘要:

Pruning is a legitimate method for reducing the size of a neural network to fit in low SWaP hardware, but the networks must be trained and pruned offline. We propose an algorithm, Artificial Neurogenesis (ANG), that grows rather than prunes the network and enables neural networks to be trained and executed in low SWaP embedded hardware. ANG accomplishes this by using the training data to determine critical connections between layers before the actual training takes place. Our experiments use a modified LeNet-5 as a baseline neural network that achieves a test accuracy of 98.74% using a total of 61,160 weights. An ANG grown network achieves a test accuracy of 98.80% with only 21,211 weights.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑