等変性 is a mathematical property often encountered in the fields of 機械学習 and コンピュータビジョン, particularly in the context of ニューラルネットワーク and transformations of data. A function is said to be equivariant if it commutes with a transformation, meaning that applying a transformation to the input and then passing it through the function yields the same result as first passing the input through the function and then applying the transformation to the output.
より正式には、関数 f and a transformation T, we say that f is equivariant to T ならば：
f(T(x)) = T(f(x))
すべての入力 x. This property is particularly useful in scenarios where the input data can be transformed in various ways, such as rotating, scaling, or translating images. In such cases, maintaining equivariance ensures that the function’s output remains consistent and predictable despite changes to the input. This is critical in applications like image recognition, where the position or orientation of an object should not affect the ability of the model to recognize it.
の文脈で、等変性はしばしば architecture of 畳み込みニューラルネットワーク (CNNs), where the 畳み込み演算 is designed to be equivariant to translations. This means that if an image is shifted, the feature maps produced by the CNN will shift accordingly, preserving the spatial information necessary for effective learning and inference.
Equivariance can also extend to other transformations, such as rotations and reflections, and is a foundational concept in various areas of AI research, including invariant 特徴抽出 そして学習モデルの対称性。