Analysis and Comparison of Different Learning Algorithms for Pattern Association Problems
1987
We investigate the behavior of different learning algorithms for networks of neuron-like units. As test cases we use simple pattern association problems, such as the XOR-problem and symmetry detection problems. The algorithms considered are either versions of the Boltzmann machine learning rule or based on the backpropagation of errors. We also propose and analyze a generalized delta rule for linear threshold units. We find that the performance of a given learning algorithm depends strongly on the type of units used. In particular, we observe that networks with ±1 units quite generally exhibit a significantly better learning behavior than the corresponding 0,1 versions. We also demonstrate that an adaption of the weight-structure to the symmetries of the problem can lead to a drastic increase in learning speed.
Keywords:
- Machine learning
- Artificial intelligence
- Active learning (machine learning)
- Semi-supervised learning
- Instance-based learning
- Online machine learning
- Stability (learning theory)
- Weighted Majority Algorithm
- Algorithm
- Wake-sleep algorithm
- Mathematics
- Learning rule
- Computer science
- Theoretical computer science
- Unsupervised learning
- Competitive learning
- Computational learning theory
- Learning classifier system
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
2
References
5
Citations
NaN
KQI