α-EM learning and its cookbook: From mixture-of-expert neural networks to movie random field

Yasuo Matsuyama, Takayuki Ikeda, Tomoaki Tanaka, Satoshi Furukawa, Naoki Takeda, Takeshi Niimoto

    研究成果: Conference contribution

    2 被引用数 (Scopus)

    抄録

    The α-EM algorithm is a proper extension of the traditional log-EM algorithm. This new algorithm is based on the α-logarithm, while the traditional one uses the logarithm. The case of α = -1 corresponds to the log-EM algorithm. Since the speed of the α-EM algorithm was reported for learning problems, this paper shows that closed-form E-steps can be obtained for a wide class of problems. There is a set of common techniques. That is, a cookbook for the α-EM algorithm is presented. The recipes include unsupervised neural networks, supervised neural networks for various gating, hidden Markov models and Markov random fields for moving object segmentation. Reasoning for the speedup is also given.

    本文言語English
    ホスト出版物のタイトルProceedings of the International Joint Conference on Neural Networks
    Place of PublicationUnited States
    出版社IEEE
    ページ1368-1373
    ページ数6
    2
    出版ステータスPublished - 1999
    イベントInternational Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA
    継続期間: 1999 7 101999 7 16

    Other

    OtherInternational Joint Conference on Neural Networks (IJCNN'99)
    CityWashington, DC, USA
    Period99/7/1099/7/16

    ASJC Scopus subject areas

    • Software

    フィンガープリント 「α-EM learning and its cookbook: From mixture-of-expert neural networks to movie random field」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

    引用スタイル