arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.03648cs.LGcs.NE
收藏

深度神经网络中的过采样

Over-Sampling in a Deep Neural Network

Surrey University(萨里大学)

Andrew J. R. Simpson

摘要:

深度神经网络(DNN)是解决诸如计算机视觉和听觉等许多工程问题的最新技术。DNN成功的一个关键因素是可扩展性-更大的网络工作得更好。然而,这种可扩展性的原因还没有很好地理解。在这里,我们将DNN解释为一个离散系统,由线性滤波器和非线性激活组成,服从采样理论的定律。在这种情况下,我们证明了过采样网络更具选择性,学习速度更快,学习更鲁棒。我们的发现最终可能会推广到人类大脑。

英文摘要:

Deep neural networks (DNN) are the state of the art on many engineering problems such as computer vision and audition. A key factor in the success of the DNN is scalability - bigger networks work better. However, the reason for this scalability is not yet well understood. Here, we interpret the DNN as a discrete system, of linear filters followed by nonlinear activations, that is subject to the laws of sampling theory. In this context, we demonstrate that over-sampled networks are more selective, learn faster and learn more robustly. Our findings may ultimately generalize to the human brain.

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。

↑