The "Liquid Computer": A Novel Strategy for Real-Time Computing on Time Series

  • strict warning: Non-static method view::load() should not be called statically in /var/www/html/drupal-6.32/sites/all/modules/views/views.module on line 906.
  • strict warning: Declaration of views_handler_filter::options_validate() should be compatible with views_handler::options_validate($form, &$form_state) in /var/www/html/drupal-6.32/sites/all/modules/views/handlers/ on line 607.
  • strict warning: Declaration of views_handler_filter::options_submit() should be compatible with views_handler::options_submit($form, &$form_state) in /var/www/html/drupal-6.32/sites/all/modules/views/handlers/ on line 607.
  • strict warning: Declaration of views_plugin_row::options_validate() should be compatible with views_plugin::options_validate(&$form, &$form_state) in /var/www/html/drupal-6.32/sites/all/modules/views/plugins/ on line 134.
  • strict warning: Declaration of views_plugin_row::options_submit() should be compatible with views_plugin::options_submit(&$form, &$form_state) in /var/www/html/drupal-6.32/sites/all/modules/views/plugins/ on line 134.
TitleThe "Liquid Computer": A Novel Strategy for Real-Time Computing on Time Series
Publication TypeJournal Article
Year of Publication2002
AuthorsNatschläger, T., W. Maass, and H. Markram
JournalSpecial Issue on Foundations of Information Processing of {TELEMATIK}

We will discuss in this survey article a new framework for analysing computations on time series and in particular on spike trains, introduced in (Maass et. al. 2002). In contrast to common computational models this new framework does not require that information can be stored in some stable states of a computational system. It has recently been shown that such models where all events are transient can be successfully applied to analyse computations in neural systems and (independently) that the basic ideas can also be used to solve engineering tasks such as the design of nonlinear controllers. Using an illustrative example we will develop the main ideas of the proposed model. This illustrative example is generalized and cast into a rigorous mathematical model: the Liquid State Machine. A mathematical analysis shows that there are in principle no computational limitations of liquid state machines in the domain of time series computing. Finally we discuss several successful applications of the framework in the area of computational neuroscience and in the field of artificial neural networks.