论文标题
等高的高斯过程和卷积神经网络的相互关系
Interrelation of equivariant Gaussian processes and convolutional neural networks
论文作者
论文摘要
目前，基于神经网络（NN）与高斯过程（GP）之间的关系，机器倾斜（ML）的新趋势相当有希望的新趋势，包括许多相关的子主题，例如NNS中的信号传播，NNS的理论衍生曲线，NNS的理论推导NNS，ML中的QFT方法，ML等的重要特征等。输入数据的对称转换。在这项工作中，我们建立了与二维欧几里得组的多个通道极限之间的关系，具有载体值为神经元激活与相应的独立引入的e象高斯流程（GP）之间的关系。
Currently there exists rather promising new trend in machine leaning (ML) based on the relationship between neural networks (NN) and Gaussian processes (GP), including many related subtopics, e.g., signal propagation in NNs, theoretical derivation of learning curve for NNs, QFT methods in ML, etc. An important feature of convolutional neural networks (CNN) is their equivariance (consistency) with respect to the symmetry transformations of the input data. In this work we establish a relationship between the many-channel limit for CNNs equivariant with respect to two-dimensional Euclidean group with vector-valued neuron activations and the corresponding independently introduced equivariant Gaussian processes (GP).
