---
title: "Recurrent Neural Networks for Sequence Production"
authors:
  - "Joachim Diederich"
  - "Markus Wasserschaff"
doi: ""
url: "https://ijcai.org/proceedings/1993/154"
pdf: "https://ijcai.org/proceedings/1993/0154.pdf"
venue: "Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence"
year: 1993
pages: "1114-1118"
track: "Machine Learning"
keywords:
---

# Recurrent Neural Networks for Sequence Production

Joachim Diederich, Markus Wasserschaff

*Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence*, pages 1114-1118.

## Abstract

In an empirical study, simple recurrent networks (SRN s, Elman, 1990) and recurrent cascade correlation networks (RCC, Fahlman, 1991) are compared with respect to a sequence production task. The application system that includes these networks extracts relevant information from incoming e-mail messages during a training period, learns the reaction to the incoming message, i.e., a sequence of user actions, and uses the learned representation for the proposal and preparation of user reactions. The performance of both network architectures in terms of network size and learning speed for a given data set is examined. Our results show that (1) RCC generates smaller networks with better performance compared to SRNs and (2) learns significantly faster than SRNs.