Approximation of relation functions and attention mechanisms

arXiv:2402.08856v1 Announce Type: new
Abstract: Inner products of neural network feature maps arises in a wide variety of machine learning frameworks as a method of modeling relations between inputs. This work studies the approximation properties of inner products of neural networks. It is shown that the inner product of a multi-layer perceptron with itself is a universal approximator for symmetric positive-definite relation functions. In the case of asymmetric relation functions, it is shown that the inner product of two different …

abstract approximation arxiv attention attention mechanisms cs.lg feature frameworks functions inputs layer machine machine learning maps modeling network networks neural network neural networks perceptron product products relations stat.ml studies type work