AISLEX: Approximate individual sample learning entropy with JAX
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60076658%3A12310%2F24%3A43909522" target="_blank" >RIV/60076658:12310/24:43909522 - isvavai.cz</a>
Alternative codes found
RIV/68407700:21220/24:00379443
Result on the web
<a href="https://www.sciencedirect.com/science/article/pii/S2352711024002851?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S2352711024002851?via%3Dihub</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.softx.2024.101915" target="_blank" >10.1016/j.softx.2024.101915</a>
Alternative languages
Result language
angličtina
Original language name
AISLEX: Approximate individual sample learning entropy with JAX
Original language description
We present AISLEX, an online anomaly detection module based on the Learning Entropy algorithm, a novel machine learning-based information measure that quantifies the learning effort of neural networks. AISLEX detects anomalous data samples when the learning entropy value is high. The module is designed to be readily usable, with both NumPy and JAX backends, making it suitable for various application fields. The NumPy backend is optimized for devices running Python3, prioritizing limited memory and CPU usage. In contrast, the JAX backend is optimized for fast execution on CPUs, GPUs, and TPUs but requires more computational resources. AISLEX also provides extensive implementation examples in Jupyter notebooks, utilizing in-parameterlinear-nonlinear neural architectures selected for their low data requirements, computational simplicity, convergence analyzability, and dynamical stability.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/LUABA22069" target="_blank" >LUABA22069: Research partnership: optimization of production processes in the chemical industry by artificial intelligence</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
SoftwareX
ISSN
2352-7110
e-ISSN
2352-7110
Volume of the periodical
28
Issue of the periodical within the volume
DEC 2024
Country of publishing house
NL - THE KINGDOM OF THE NETHERLANDS
Number of pages
6
Pages from-to
—
UT code for WoS article
001334415900001
EID of the result in the Scopus database
2-s2.0-85205543334