This paper introduces a novel representation of convolutional Neural Networks (CNNs) in terms of 2-D dynamical systems. To this end, the usual description of convolutional layers with convolution kernels, i.e., the impulse responses of linear filters, is realized in state space as a linear time-invariant 2-D system. The overall convolutional Neural Network composed of convolutional layers and nonlinear activation functions is then viewed as a 2-D version of a Lur'e system, i.e., a linear dynamical system interconnected with static nonlinear components. One benefit of this 2-D Lur'e system perspective on CNNs is that we can use robust control theory much more efficiently for Lipschitz constant estimation than previously possible.
翻译:本文介绍了以 2 - D 动态 系统 的 革命神经网络(CNNs ) 的新表述。 为此, 以 线性过滤器的脉冲反应作为线性时间变换 2 - D 系统在州空间内实现了对 革命性神经网络(CNNs ) 的常规描述。 由 革命性 层和非线性激活功能组成的整个 革命性神经网络 被看作 卢尔系统 2 - D 版本, 即 线性动态系统, 与静态非线性组件相连接 。 在CNN 上, 2 - D Lur 系统视角的一个好处是, 我们比以往更高效地运用强力控制理论来进行利普施茨 持续估算 。</s>