ISSN :XXXX-XXX

Learning causation event conjunction sequences

Original Research (Published On: 23-Jun-2024 )
Learning causation event conjunction sequences

Thomas E. Portegys

Adv. Artif. Intell. Mach. Learn., 1 (1):1-12

Thomas E. Portegys : Dialectek

Download PDF Here

Article History: Received on: 07-Apr-24, Accepted on: 16-Jun-24, Published on: 23-Jun-24

Corresponding Author: Thomas E. Portegys

Email: portegys@gmail.com

Citation: Thomas E. Portegys (2024). Learning causation event conjunction sequences. Adv. Artif. Intell. Mach. Learn., 1 (1 ):1-12


Abstract

    

This is an examination of some methods that learn causations in event sequences. A causation is defined as a conjunction of one or more cause events occurring in an arbitrary order, with possible intervening non-causal events, that lead to an effect. The methods include recurrent and non-recurrent artificial neural networks (ANNs), as well as a histogram-based algorithm. An attention recurrent ANN performed the best of the ANNs, while the histogram algorithm was significantly superior to all the ANNs.

Statistics

   Article View: 78
   PDF Downloaded: 4