Seminar iz veštačke inteligencije, 13. april 2022.

Naredni sastanak Seminara biće održan onlajn u sredu, 13. aprila 2022, od 19-20 časova.

Predavači: Piotr A. Kowalski, Faculty of Physics and Applied Computer Science, AGH University of Science and Technology; Systems Research Institute, Polish Academy of Sciences

Naslov predavanja: SENSITIVITY ANALYSIS FOR ARTIFICIAL NEURAL NETWORK STRUCTURE REDUCTION

Apstrakt:
In the seminar, I will show some propositions of the use of sensitivity analysis (SA) for the structure reduction of the selected neural network topologies. Two algorithms are introduced. The first algorithm applies SA for the neural network input layer reduction by selecting significant features of input patterns. The second algorithm utilizes the SA procedure to remove redundant neurons of the network. The classification qualities of reduced and full structure neural networks are compared. Furthermore, we set for comparison the neural networks for which different state-of-the-art reduction methods are applied both in the input layer and pattern layer. The models are tested in the classification problems of some repository data sets.

Napomena: Registraciona forma za učešće je dostupna na linku:
https://miteam.mi.sanu.ac.rs/asset/CW5nJWDSEZDj7p32p

Ukoliko želite samo da pratite predavanje bez mogućnosti aktivnog učešća, prenos je dostupan na linku:
https://miteam.mi.sanu.ac.rs/asset/4LNW8WtML7rLKojoz



Nažalost nije moguće ostaviti komentar.