Name
Abstract | ||
|---|---|---|
In the past decades, a number of genetic programming techniques have been developed to evolve machine instructions. However, these approaches typically suffer from a lack of scalability that seriously impairs their applicability to real-world scenarios. In this paper, a novel self-scaling instruction generation method is introduced, which tries to overcome the scalability issue by using Cartesian Genetic Programming. In the proposed method, a dual-layer network architecture is created: one layer is used to evolve a series of instructions while the other is dedicated to the generation of loop control parameters. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1007/978-3-642-20407-4_26 | EuroGP |
Keywords | Field | DocType |
self-scaling instruction generator,machine instruction,instruction generation method,past decade,dual-layer network architecture,genetic programming technique,loop control parameter,scalability issue,cartesian genetic programming,network architecture | Loop control,Computer science,Network architecture,Genetic programming,Theoretical computer science,Cartesian genetic programming,Artificial intelligence,Genetic representation,Scaling,Machine learning,Scalability | Conference |
Volume | ISSN | Citations |
6621 | 0302-9743 | 3 |
PageRank | References | Authors |
0.70 | 11 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yang Liu | 1 | 11 | 2.31 |
| Gianluca Tempesti | 2 | 457 | 57.09 |
| James A. Walker | 3 | 3 | 0.70 |
| Jon Timmis | 4 | 1237 | 120.32 |
| Andrew M. Tyrrell | 5 | 326 | 49.07 |
| Paul Bremner | 6 | 7 | 2.14 |