Publications
Talk · IOP Conference Series Materials Science and Engineering · September 1, 2020
The choice of informative features based on heterogeneous functionals
Narzillo Mamatov, Nilufar A’loxanovna Niyozmatova, Abdurashid Samijonov, Sh Juraev, B. M. Abdullayeva
Abstract
Abstract One of the classical problems of the theory of pattern recognition is to reduce the dimension of the original feature space from dimension N to dimension N’, N’ < N. In the first works on pattern recognition, the task was to construct an informativeness criterion that maps N-dimensional to a space of lower dimension so that a solution can be made in this space. One of the advantages of this criterion is that the classification in a space of lower dimension is faster and easier, and the criterion of being constructed once.
Face and Expression RecognitionStatistical Methods and ApplicationsNeural Networks and Applicationsfeature selectiondimensionality reductionpattern recognition
More by Narzillo Mamatov
- Margin-Guided Adaptive Model Routing for Resource-Efficient Speaker Verification on Edge DevicesComputation · 2026
- New Recursive Divided-Difference Interpolation MethodResearch Square · 2026
- Noise reduction and quality assessment in images using quantum computing based on artificial intelligence agentsInternational Conference on Digital Technologies, Optics, and Materials Science · 2026
- Modeling of blockchain technology-based hybrid secure communication system using autonomous artificial intelligence agentsInternational Conference on Digital Technologies, Optics, and Materials Science · 2026