Neural networks and rational McNaughton functions

被引：0
|
作者：
Amato, P
Di Nola, A
Gerla, B
机构：
[1] Univ Salerno, Dept Math & Informat, Soft Comp Lab, I-84081 Baronissi, SA, Italy
[2] STMicroelect, SST Corp R& D, I-80022 Arzano, Napoli, Italy
来源：
JOURNAL OF MULTIPLE-VALUED LOGIC AND SOFT COMPUTING | 2005年 / 11卷 / 1-2期
关键词：
neural networks; many-valued logic; Lukasiewicz logic; rational weights; McNaughton functions;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper we shall describe a correspondence between Rational McNaughton functions (as truth table of Rational Lukasiewicz formulas) and neural networks in which the activation function is the truncated identity and synaptic weights are rational numbers. On one hand to have a logical representation (in a given logic) of neural networks could widen the interpretability, amalgamability and reuse of these objects. On the other hand, neural networks could be used to learn formulas from data and as circuital counterparts of (functions represented by) formulas.
引用
收藏
页码：95 / 110
页数：16
相关论文
共 50 条
  • [31] Neural networks for determining affinity functions
    Dmitrienko, Valery Dmitrievich
    Zakovorotniy, Alexander Yurievich
    Leonov, Sergey Yurievich
    2ND INTERNATIONAL CONGRESS ON HUMAN-COMPUTER INTERACTION, OPTIMIZATION AND ROBOTIC APPLICATIONS (HORA 2020), 2020, : 647 - 651
  • [32] Approximation by Neural Networks with Sigmoidal Functions
    Dan Sheng YU
    ActaMathematicaSinica, 2013, 29 (10) : 2013 - 2026
  • [33] Realization theory of recurrent neural networks and rational systems
    Defourneau, Thibault
    Petreczky, Mihaly
    2019 IEEE 58TH CONFERENCE ON DECISION AND CONTROL (CDC), 2019, : 8048 - 8053
  • [34] Riesz-McNaughton functions and Riesz MV-algebras of nonlinear functions
    Di Nola, Antonio
    Lenzi, Giacomo
    Vitale, Gaetano
    FUZZY SETS AND SYSTEMS, 2017, 311 : 1 - 14
  • [35] Adaptive learning of rational expectations using neural networks
    Heinemann, M
    JOURNAL OF ECONOMIC DYNAMICS & CONTROL, 2000, 24 (5-7): : 1007 - 1026
  • [36] ZETA-FUNCTIONS OF RATIONAL FUNCTIONS ARE RATIONAL
    HINKKANEN, A
    ANNALES ACADEMIAE SCIENTIARUM FENNICAE-MATHEMATICA, 1994, 19 (01): : 3 - 10
  • [37] Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions
    Jagtap, Ameya D.
    Shin, Yeonjong
    Kawaguchi, Kenji
    Karniadakis, George Em
    NEUROCOMPUTING, 2022, 468 (165-180) : 165 - 180
  • [38] Quantum activation functions for quantum neural networks
    Marco Maronese
    Claudio Destri
    Enrico Prati
    Quantum Information Processing, 21
  • [39] Characteristic functions and process identification by neural networks
    Dente, JA
    Mendes, RV
    NEURAL NETWORKS, 1997, 10 (08) : 1465 - 1471
  • [40] Constructive approximation of discontinuous functions by neural networks
    Llanas, B.
    Lantaron, S.
    Sainz, F. J.
    NEURAL PROCESSING LETTERS, 2008, 27 (03) : 209 - 226
12345