Abstract | ||
---|---|---|
This paper attempts to argue that most adaptive systems, such as evolutionary or learning systems, have inherently multiple
objectives to deal with. Very often, there is no single solution that can optimize all the objectives. In this case, the concept
of Pareto optimality is key to analyzing these systems.
To support this argument, we first present an example that considers the robustness and evolvability trade-off in a redundant
genetic representation for simulated evolution. It is well known that robustness is critical for biological evolution, since
without a sufficient degree of mutational robustness, it is impossible for evolution to create new functionalities. On the
other hand, the genetic representation should also provide the chance to find new phenotypes, i.e., the ability to innovate.
This example shows quantitatively that a trade-off between robustness and innovation does exist in the studied redundant representation.
Interesting results will also be given to show that new insights into learning problems can be gained when the concept of
Pareto optimality is applied to machine learning. In the first example, a Pareto-based multi-objective approach is employed
to alleviate catastrophic forgetting in neural network learning. We show that learning new information and memorizing learned
knowledge are two conflicting objectives, and a major part of both information can be memorized when the multi-objective learning
approach is adopted. In the second example, we demonstrate that a Pareto-based approach can address neural network regularizationmore
elegantly. By analyzing the Pareto-optimal solutions, it is possible to identifying interesting solutions on the Pareto front. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/s11704-009-0004-8 | Frontiers of Computer Science in China |
Keywords | Field | DocType |
Pareto analysis,multi-objective optimization,evolution,evolvability,robustness,learning,accuracy,complexity | Mathematical optimization,Adaptive system,Computer science,Evolvability,Robustness (computer science),Multi-objective optimization,Artificial intelligence,Pareto analysis,Machine learning,Pareto principle | Journal |
Volume | Issue | ISSN |
3 | 1 | 1673-7350 |
Citations | PageRank | References |
3 | 0.38 | 14 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yaochu Jin | 1 | 6457 | 330.45 |
Robin Gruna | 2 | 14 | 4.50 |
Bernhard Sendhoff | 3 | 2272 | 240.31 |