Combining the perception algorithm with logarithmic simulated annealing

A. Albrecht, C.K. Wong

    Research output: Contribution to journalArticlepeer-review

    9 Citations (Scopus)


    We present results of computational experiments with an extension of the Perceptron algorithm by a special type of simulated annealing. The simulated annealing procedure employs a logarithmic cooling schedule (-), where (-) is a parameter that depends on the underlying configuration space. For sample sets S of n-dimensional vectors generated by randomly chosen polynomials (-), we try to approximate the positive and negative examples by linear threshold functions. The approximations are computed by both the classical Perceptron algorithm and our extension with logarithmic cooling schedules. For (-) and (-), the extension outperforms the classical Perceptron algorithm by about 15% when the sample size is sufficiently large. The parameter was chosen according to estimations of the maximum escape depth from local minima of the associated energy landscape.
    Original languageEnglish
    Pages (from-to)75-83
    JournalNeural Processing Letters
    Issue number1
    Publication statusPublished - 2001


    • cooling schedules
    • neural networks
    • perceptron algorithm
    • simulated annealing
    • threshold functions


    Dive into the research topics of 'Combining the perception algorithm with logarithmic simulated annealing'. Together they form a unique fingerprint.

    Cite this