Sequence Processing Neural Network withQ-States Monotonic Transfer Function | Zendy

Katsuki Katayama | Zendy; Tsuyoshi Horiguchi | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Sequence Processing Neural Network withQ-States Monotonic Transfer Function

Author(s) -

Katsuki Katayama,

Tsuyoshi Horiguchi

Publication year - 2005

Publication title -

progress of theoretical physics supplement

Language(s) - English

Resource type - Journals

ISSN - 0375-9687

DOI - 10.1143/ptps.157.266

Subject(s) - monotonic function , function (biology) , binary number , sequence (biology) , representation (politics) , artificial neural network , transfer function , transfer (computing) , generating function , zero (linguistics) , algorithm , path (computing) , mathematics , computer science , discrete mathematics , artificial intelligence , arithmetic , mathematical analysis , chemistry , engineering , philosophy , law , linguistics , biology , biochemistry , evolutionary biology , parallel computing , political science , programming language , politics , electrical engineering

Storage capacity as for retrieval of sequences of binary patterns is investigated for a fully connected neural network with Q (> 2)-states. By using a generating-function method of path-integral representation, we find that the network with Q-states monotonic transfer function retrieves more sequences of the stored patterns than that with a binary monotonic transfer function at zero temperature, if the control parameter is chosen optimally. We compare the results obtained by the analytic method with those by numerical simulations.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research