JsonGrinder.jl: Automated Differentiable Neural Architecture for Embedding Arbitrary JSON Data
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00363523" target="_blank" >RIV/68407700:21230/22:00363523 - isvavai.cz</a>
Result on the web
<a href="https://jmlr.org/papers/v23/21-0174.html" target="_blank" >https://jmlr.org/papers/v23/21-0174.html</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
JsonGrinder.jl: Automated Differentiable Neural Architecture for Embedding Arbitrary JSON Data
Original language description
Standard machine learning (ML) problems are formulated on data converted into a suitable tensor representation. However, there are data sources, for example in cybersecurity, that are naturally represented in a unifying hierarchical structure, such as XML, JSON, and Protocol Buffers. Converting this data to a tensor representation is usually done by manual feature engineering, which is laborious, lossy, and prone to bias originating from the human inability to correctly judge the importance of particular features. JsonGrinder.jl is a library automating various ML tasks on these difficult sources. Starting with an arbitrary set of JSON samples, it automatically creates a differentiable ML model (called hmilnet), which embeds raw JSON samples into a fixed-size tensor representation. This embedding network can be naturally extended by an arbitrary ML model expecting tensor inputs in order to perform classification, regression, or clustering.
Czech name
—
Czech description
—
Classification
Type
J<sub>SC</sub> - Article in a specialist periodical, which is included in the SCOPUS 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
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Journal of Machine Learning Research
ISSN
1532-4435
e-ISSN
—
Volume of the periodical
23
Issue of the periodical within the volume
September
Country of publishing house
US - UNITED STATES
Number of pages
5
Pages from-to
1-5
UT code for WoS article
—
EID of the result in the Scopus database
2-s2.0-85148099476