Keywords
Affiliated Institutions
Related Publications
A study of the behavior of several methods for balancing machine learning training data
There are several aspects that might influence the performance achieved by existing learning systems. It has been reported that one of these aspects is related to class imbalanc...
The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks
To date, the preponderance of techniques for eliciting the knowledge embedded in trained artificial neural networks (ANN's) has focused primarily on extracting rule-based explan...
Does cost-sensitive learning beat sampling for classifying rare classes?
A highly-skewed class distribution usually causes the learned classifier to predict the majority class much more often than the minority class. This is a consequence of the fact...
Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-Based Optimization to Spiking Neural Networks
Spiking neural networks (SNNs) are nature's versatile solution to fault-tolerant, energy-efficient signal processing. To translate these benefits into hardware, a growing number...
Neural GPUs Learn Algorithms
Abstract: Learning an algorithm from examples is a fundamental problem that has been widely studied. Recently it has been addressed using neural networks, in particular by Neura...
Publication Info
- Year
- 1994
- Type
- book-chapter
- Pages
- 37-45
- Citations
- 311
- Access
- Closed
External Links
Social Impact
Social media, news, blog, policy document mentions
Citation Metrics
Cite This
Identifiers
- DOI
- 10.1016/b978-1-55860-335-6.50013-1