Artificial neural nets and genetic algorithms. ICANNGA 97. Proceedings of the 3rd international conference in Norwich, GB, April 2--4, 1997 (Q4231044)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 1259208
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Artificial neural nets and genetic algorithms. ICANNGA 97. Proceedings of the 3rd international conference in Norwich, GB, April 2--4, 1997 |
scientific article; zbMATH DE number 1259208 |
Statements
9 March 1999
0 references
Norwich (GB)
0 references
Conference
0 references
Genetic algorithms
0 references
Artificial neural nets
0 references
Proceedings
0 references
telecommunications
0 references
0.8646345734596252
0 references
Artificial neural nets and genetic algorithms. ICANNGA 97. Proceedings of the 3rd international conference in Norwich, GB, April 2--4, 1997 (English)
0 references
The articles of this volume will not be indexed individually. From the introduction: This is the third in a series of conferences devoted primarily to the theory and applications of artificial neural networks and genetic algorithms. This series of conferences is uinique in recognizing the relation between the two main themes of artificial neural networks and genetic algorithms, each having its origin in a natural process fundamental to life on earth, and each now well established as a paradigm fundamental to continuing technological development through the solution of complex, industrial, commercial and financial problems. This is well illustrated in this volume by the numerous applications of both paradigms to new and challenging problems. The third key theme of the series, therefore, is the integration of both technologies, either through the use of the genetic algorithm to construct the most effective network architecture for the problem in hand, or, more recently, the use of neural networks as approximate fitness functions for a genetic algorithm searching for good solutions in an `incomplete' solution space, i.e. one for which the fitness is not easily established for every possible solution instance. Turning to the contributions, of particular interest is the number of contributions devoted to the development of `modular' neural networks, where a divide and conquer approach is adopted and each module is trained to solve a part of the problem. Contributions also abound in the field of robotics and, in particular, evolutionary robotics, in which the controllers are adapted through the use of some evolutionary process. This latter field also provided a forum for contributions using other related technologies, such as fuzzy logic and reinforcement learning. Furthermore, we note the relatively large number of contributions in telecommunications related research, confirming the rapid growth in this industry and the associated emergence of difficult optimization problems. The increasing complexity of problems in this and other areas has prompted researchers to harness the power of other heuristic techniques, such as simulated annealing and tabu search, either in their `pure' form or as hybrids. The contributions in this volume reflect this trend. Finally, we are also pleased to continue to provide a forum for contributions in the burgeoning and exciting field of evolutionary hardware.
0 references