Abstract
This paper proposes a hybrid approach that integrates Genetic Algorithms (GA) with derivative-based training for Multi-Layer Perceptron (MLP) neural networks in the Dinosaur Game environment. GA is employed to generate training data in the absence of existing datasets, and the performance of derivative-based MLP models trained on this data is evaluated. The performances of the various network architectures have been compared with respect to network structure and activation functions. The generalization capability of the network architectures has been assessed on tampered test environment.
| Original language | English |
|---|---|
| Title of host publication | ICHORA 2025 - 2025 7th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Electronic) | 9798331510886 |
| DOIs | |
| Publication status | Published - 2025 |
| Event | 7th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, ICHORA 2025 - Ankara, Turkey Duration: 23 May 2025 → 24 May 2025 |
Publication series
| Name | ICHORA 2025 - 2025 7th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings |
|---|
Conference
| Conference | 7th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, ICHORA 2025 |
|---|---|
| Country/Territory | Turkey |
| City | Ankara |
| Period | 23/05/25 → 24/05/25 |
Bibliographical note
Publisher Copyright:© 2025 IEEE.
Keywords
- Data Generation
- Dinosaur Game
- Genetic Algorithms
- Hybrid Approach
- Multi-Layer Perceptron
- Neural Networks
Fingerprint
Dive into the research topics of 'Bridging Genetic Algorithms and Gradient-Based Learning: A Case Study on the Dinosaur Game'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver