Neural networks in natural sciences

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13440%2F23%3A43898260" target="_blank" >RIV/44555601:13440/23:43898260 - isvavai.cz</a>
Result on the web
<a href="https://ans2023.ucm.sk/" target="_blank" >https://ans2023.ucm.sk/</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Neural networks in natural sciences
Original language description
Artificial neural networks (ANNs) have emerged as powerful tools for addressing complex problems invarious fields, including the natural sciences. This contribution involves an exploration of the applications of artificialneural networks, specifically focusing on their use in both regression and classification tasks. We place particularemphasis on utilizing the autoencoder model within the context of the anomaly detection in natural sciences.The autoencoder, a type of unsupervised learning model, has gained significant attention due to its ability tocatch meaningful representations of input data. Its architecture comprises an encoder, which compresses the input datainto a lower-dimensional latent space, and a decoder, which reconstructs the original input from the encodedrepresentation. This unique characteristic of the autoencoder makes it well-suited for extracting valuable features fromhigh-dimensional scientific datasets. We will present some applications of the above-mentioned models in the naturalsciences and highlight the advantages, such as their ability to handle noisy and incomplete data.
Czech name
—
Czech description
—

Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)