| Title |
Assigningdifferent activation functions in artificial neural networks with the goal of achieving higher prediction accuracy |
| Authors |
Baravykas, Gytis ; Kardoka, Justas ; Grigaliunas, Domas ; Naujokaitis, Darius |
| Full Text |
|
| Is Part of |
CEUR workshop proceedings: IVUS 2024: Information society and university studies 2024: proceedings of the 29th international conference on information society and university studies (IVUS 2023) Kaunas, Lithuania, May 17, 2024 / edited by: I. Veitaitė, A. Lopata, T. Krilavičius, M. Woźniak.. Aachen : CEUR-WS. 2024, vol. 3885, p. 289-299.. ISSN 1613-0073 |
| Keywords [eng] |
activation functions ; artificial neural networks ; machine learning |
| Abstract [eng] |
The research paper explores the concept of using multiple activation functions in artificial neural networks and investigates their impact on model performance. The experiments conducted on various models such as AlexNet, ResNet50, TuNet, and SimpleNN reveal insights into the effectiveness of different activation function combinations. The results indicate that using multiple activation functions can lead to modest improvements in model performance, particularly in image segmentation tasks where modifications to the UNet architecture show significant enhancements. However, for time series regression/forecasting tasks, the experiments demonstrate that using multiple activation functions does not significantly improve prediction accuracy. Therefore, the paper concludes that while there are some benefits to using multiple activation functions in certain scenarios, the choice of activation function should be based on the specific task and dataset. |
| Published |
Aachen : CEUR-WS |
| Type |
Conference paper |
| Language |
English |
| Publication date |
2024 |
| CC license |
|
