Metadata (cookie, IP address, location) may be collected for the functioning of the site. If you do not want this data processed, then you should leave the site.
AIC desktop
data analysis system without writing code
Software package for prototyping and quickly testing hypotheses in the field of machine learning and pattern recognition
For the implementation of student scientific projects as well as for assistance in writing dissertations. Focused on image classification tasks and analysis of anonymized biomedical and biometric signals
Key Features
Data Analysis and Pattern Recognition
Data analysis uses mathematical statistics methods to identify patterns. You can solve problems of classification, feature extraction, and image generation based on the Monte Carlo method. Many ways to create classifiers based on artificial neural networks and other machine learning models have been implemented.
Neural network designers and classifier ensembles
The visual editor allows you to create complex architectures of multilayer neural networks (convolutional, fully connected, and hybrid). Neural networks can be combined into ensembles and integrated with other (including non-network) models.
Reliability of assessments and metrics
The probabilities of type 1 and type 2 errors, as well as recognition accuracy, can be assessed in different ways, taking into account many parameters, which allows you to obtain results with high reliability. Both direct numerical experiments and testing according to GOST R 52633.3 are supported.
Biometric technologies
Using the program, it is easy to simulate biometric authentication and identification systems based on neural network biometric-code converters (BBC), trained according to the Russian standard GOST R 52633.5
Data formats
Information about images can be loaded in the form of feature vectors (xml, txt) and in the form of raw (unlabeled, partially labeled) data (bmp, wav, edf, csv, etc.) related to any subject area (sound, images, thermograms, echograms, ECG, EEG, biometric and biomedical images, etc.). After downloading, the data is converted into a unified format.

Examples of using AIC desktop

Intellectual property

Made on