article · 2003

Subgoal chaining and the local minimum problem

Cited by 4Abstract and details only

Abstract

It is well known that performing gradient descent method on fixed surfaces may result in poor travel through getting stuck in local minima and other surface features. Subgoal chaining in supervised learning is a method to improve travel for neural networks by directing local variation in the surface during training. This paper shows that linear subgoal chains such as those used in ERA are not sufficient to overcome the local minimum problem and examines nonlinear subgoal chains as a possible alternative.

Cite this paper

APA 7

Lewis, J. P., & Weir, M. (2003). Subgoal chaining and the local minimum problem. https://doi.org/10.1109/ijcnn.1999.832660

MLA 9

Lewis, Jonathan P., and Michael Weir. “Subgoal chaining and the local minimum problem.” vol. 3, 2003, pp. 1844–49, https://doi.org/10.1109/ijcnn.1999.832660.

Chicago

Lewis, Jonathan P., and Michael Weir. 2003. “Subgoal chaining and the local minimum problem.” https://doi.org/10.1109/ijcnn.1999.832660.

Harvard

Lewis, J.P. and Weir, M. (2003) ‘Subgoal chaining and the local minimum problem’. Available at: https://doi.org/10.1109/ijcnn.1999.832660.

BibTeX

@article{lewis2003subgoal,
  title = {{Subgoal chaining and the local minimum problem}},
  author = {Lewis, Jonathan P. and Weir, Michael},
  volume = {3},
  pages = {1844--1849},
  year = {2003},
  doi = {10.1109/ijcnn.1999.832660}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.