FIELD: computer equipment.
SUBSTANCE: group of inventions can be used to classify data sets. Method comprises steps of receiving data having at least one feature from a set of features, wherein the received data comprises at least one training example, applying at least one trained low-dimensional classifier to the received data and assigning weight coefficients for each of said at least one trained low-dimensional classifier and outputting the weighted sum, wherein the weighting factors depend on the presence or absence of the input attribute in the received data.
EFFECT: providing reliable analysis and classification thereof even if missing or incomplete data are available.
15 cl, 6 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD AND APPARATUS FOR AUTOMATICALLY SUMMARISING CONTENTS OF ELECTRONIC DOCUMENTS | 2012 |
|
RU2595594C2 |
| RELEVANCY ASSESSMENT FOR ARTIFICIAL NEURAL NETWORKS | 2015 |
|
RU2703343C2 |
| CLASSIFICATION OF SAMPLES DATA | 2009 |
|
RU2517286C2 |
| VOLUME EQUALIZER CONTROLLER AND CONTROL METHOD | 2014 |
|
RU2612728C1 |
| LOUDNESS EQUALIZER CONTROLLER AND CONTROL METHOD | 2021 |
|
RU2826268C2 |
| VOLUME LEVELING CONTROLLER AND THE CONTROL METHOD | 2014 |
|
RU2746343C2 |
| METHODS FOR TRAINING DEEP CONVOLUTIONAL NEURAL NETWORKS BASED ON DEEP LEARNING | 2018 |
|
RU2767337C2 |
| VOLUME EQUALIZER CONTROLLER AND CONTROL METHOD | 2014 |
|
RU2715029C2 |
| METHOD FOR ATTRIBUTION OF PARTIALLY STRUCTURED TEXTS FOR FORMATION OF NORMATIVE-REFERENCE INFORMATION | 2020 |
|
RU2750852C1 |
| SYSTEM AND METHOD FOR ARTIFICIAL NEURAL NETWORK INVARIANT TO TRANSFERRING | 2017 |
|
RU2656990C1 |
