Multi-output regression network and learning method

Abstract

The invention provides a multi-output regression network for learning the input-output relationship, a method for learning the input-output relationship based on the multi-output regression network, and a computer-readable storage medium. The multi-output regression network includes: a plurality of input nodes for receiving input data (x i ); a plurality of intermediate nodes, which form a nonlinear network layer with the plurality of input nodes, and the nonlinear network layer converts the input data (x i ) is mapped to the multiple intermediate nodes, and the multiple intermediate nodes are paired with nonlinearly mapped input data (x i ) to apply a predetermined function; and a plurality of output nodes, which form a linear network layer with the plurality of intermediate nodes, and the linear network layer applies the input data (x) of the predetermined function through linear mapping i ) is mapped to the multiple output nodes as output data (y i ) to output; wherein, the multi-output regression network passes through the given input data (x i ) and the output data (y i ) under the condition of the mapping parameter (W) of the nonlinear mapping and the mapping parameter (S) of the linear mapping are jointly optimized, and the input data (x i ) with the output data (y i )The relationship between.

Description

technical field [0001] The invention relates to the field of machine learning, in particular to a multi-output regression network for learning input-output relationship and a method for learning input-output relationship. Background technique [0002] With the explosion of deep learning, neural networks have once again become a hot spot of attention. In the field of machine learning and data mining, kernel approximation methods and multi-output regression models are currently used to describe the relationship between input and output. [0003] The kernel approximation method is to find a mapping function based on Bechner's theorem, which just corresponds to a translation-invariant kernel function. The basic principle of the kernel approximation method is that a positive definite, translation-invariant kernel function is a distributed Fourier transform. Through the decomposition of the basis function of the Fourier transform, the mapping function can be approximately express...

AI Technical Summary

Problems solved by technology

However, in most practical applications, the assumption that the regression coefficients exist in a low-dimensional manifold space in the correlation assumption model based on prior knowledge is not valid, and in different applications, it cannot be guaranteed that a linear subspace can be shared. These two points greatly limit the application of this method in real data, and this special assumption will seriously affect the system performance

Also, linear regression models do not handle nonlinear relationships between input and output well

Images