Evolved Dual Weight Neural Architectures to Facilitate Incremental Learning
By John A. Bullinaria. 2009
6 citations recorded by the source corpus.
This paper explores techniques for improving incremental learning performance for generalization tasks. The idea is to generalize well from past input-output mappings that become available in batches over time, without the need to store past batches. Standard connectionist systems have previously been optimized for this problem using an evolutionary computation approach. Here that approach is explored more generally and rigorously, and dual weight architectures are incorporated into the evolutionary neural network approach and shown to result in improved performance over existing incremental learning systems.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sebastian Risi
- Andrea Soltoggio
- Kenneth O. Stanley
- Jeff Clune
- Joel Lehman
- Jean-Baptiste Mouret
- Risto Miikkulainen
- Paul Tonelli
Citations in the corpus
- Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “It is also important to note that EPANN do not have the neurophysiological constraints of biological systems, e.g., short neural connections, sparsity, brain size limits, etc., which impacts the evolution of particular architectures such as modularity (Bullinaria, 2007b, 2009a).”
- Short-term plasticity as cause–effect hypothesis testing in distal reward learning (2014, background): “Such as distinction is not new in connectionist models (Hinton and Plaut, 1987; Schmidhuber, 1992; Levy and Bairaktaris, 1995; Tieleman and Hinton, 2009; Bullinaria, 2009), however, in the proposed study the idea is extended to model hypothesis testing and memory consolidation with distal rewards.”