發(fā)布時間：2021-10-08 20:14

　　In this paper,we consider the design of output layer nodes of multiple linear perception network for solving r-class classification problems（r≥ 3）.In general,the output layer is designed in an "one-to-one" approach.Instead,we will adopt a "binary-coding" approach to build the output layer,which contains q nodes such that 2^q-1 <r ≤2 q with q≥ 2 and outputs a binary code of the number i if an input belongs to the i-th class.In particular,for multiple linear perceptrons with four hidd... 

【文章來源】：高等學校計算數(shù)學學報. 2020,42(03)北大核心CSCD

【文章頁數(shù)】：12 頁

【文章目錄】：
1 Introduction
2 Linear perceptron and linear separability
3 Classification problem of the four-dimensional regular hypercube
4 Proofs of the main results
    4.1 Proof of Theorem 3.1
        4.1.1 Cases of 9≤r≤13
        4.1.2 Cases of 14

    4.2 Proof of Theorem 3.2
5 Conclusions



本文編號：3424882