A COMPARISON STUDY OF BINARY FEEDFORWARD NEURAL NETWORKS AND DIGITAL CIRCUITS

被引:13
作者
ANDREE, HMA [1 ]
BARKEMA, GT [1 ]
LOURENS, W [1 ]
TAAL, A [1 ]
VERMEULEN, JC [1 ]
机构
[1] NIKHEF H,AMSTERDAM,NETHERLANDS
关键词
BINARY FEEDFORWARD NEURAL NETWORKS; LOGIC CIRCUITS; HARDWIRED IMPLEMENTATION;
D O I
10.1016/S0893-6080(05)80123-6
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A comparison study was carried out between feedforward neural networks composed of binary linear threshold units and digital circuits. These networks were generated by the regular partitioning algorithm and a modified Quine-McCluskey algorithm, respectively. The size of both types of networks and their generalisation properties are compared as a function of the nearest-neighbour correlation in the binary input sets. The ratio of the number of components required by digital circuits and the number of neurons grows linearly for the input sets considered The considered neural networks do not outperform digital circuits with respect to generalisation. Sensitivity analysis leads to a preference for digital circuits, especially for increasing number of inputs. In the case of analog input sets, hybrid networks of binary neurons and logic gates are of interest.
引用
收藏
页码:785 / 790
页数:6
相关论文
共 16 条
  • [1] ALEKSANDER I, 1988, NEURAL COMPUTING ARC
  • [2] ARMSTRONG WW, SOME RESULTS ADAPTIV
  • [3] NUMERICAL STUDY OF PHASE-TRANSITIONS IN POTTS MODELS
    BARKEMA, G
    DEBOER, J
    [J]. PHYSICAL REVIEW A, 1991, 44 (12): : 8000 - 8005
  • [4] BARKEMA GT, 1992, UNPUB NEURAL NETWORK
  • [5] BOOTH TL, 1971, DIGITAL NETWORKS COM
  • [6] Dertouzos Michael, 1965, THRESHOLD LOGIC SYNT
  • [7] Frean M., 1990, NEURAL COMPUT, V2, P198
  • [8] A FAST PARTITIONING ALGORITHM AND A COMPARISON OF BINARY FEEDFORWARD NEURAL NETWORKS
    KEIBEK, SAJ
    BARKEMA, GT
    ANDREE, HMA
    SAVENIJE, MHF
    TAAL, A
    [J]. EUROPHYSICS LETTERS, 1992, 18 (06): : 555 - 559
  • [9] KOONIN SE, 1986, COMPUTATIONAL PHYSIC
  • [10] LEARNING ALGORITHMS WITH OPTIMAL STABILITY IN NEURAL NETWORKS
    KRAUTH, W
    MEZARD, M
    [J]. JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1987, 20 (11): : L745 - L752