Works & Experience

  • Brain2Text
  • Brain2Chat
  • Brain2BI
  • Pushkin

Russian neural networks (neuromodels) and Artificial intelligence works by Cognitive Systems Company


Cases based on Several multi-layer neuromodels (automated)

Brain2Text (DSSM). Example of an intelligent assistance system.

5 multi-layer Brain2Text models, trained according to the text fragment of the Sberbank strategy, consisting of 8200 words and 800 sentences, allows to perform a semantic search of query-relevant tokens for a response with an accuracy of 0.86 and synthesize from these lexemes a response in the form of a sentence with an accuracy of 0.91 (f-measure 0.9).

Online version


Cases based on multi-layer neuromodels (automated)

Brain2Chat: Virtual query service assistant.

A multi-layer Brain2Chat model, trained in 1000 question-answer pairs on the content of the fragment of the Sberbank strategy, allows to do a semantic search of query-relevant answers with an accuracy of 80%
(f-measure 0.90).

Online version
Neural networks (neuromodels)


Cases based on one multi-layer neuromodel

House Prices Kaggle Task:

The House Prices model trained for 2 minutes 33 seconds on 79 parameters of 1461 objects of real estate predicts the cost of an object with an average error < 0.42 (classification time <1sec.)

Digit Recognition (MNIST) Kaggle Task:

The model for recognition of handwritten digits (Digit Recognizer) trained for 20 minutes on 784 parameters (28x28 pixels image) for 28 000 images allows to recognize handwritten numbers with an accuracy of 81%. (classification time 1-2sec.

*Information from the Kaggle official website 1 и 2

Brain2Helpdesk (SSM). Intelligent search through the contents of files.

Three Brain2Helpdesk models were trained in 100 documents containing 1200 sentences. They allow instant semantic search of relevant documents with an accuracy of 88%.

The answer is also provided in a variative Telegram сhat-bot.

Research project

Based on Several multi-layer neuromodels

Pushkin Project

The aim of the project is to teach AI to compose poems in the style of the most prominent Russian poet (quatrains with iambic tetrameter). To do this, the company has developed models to determine and select rhymes and stresses in the word. Moreover, work is underway on a model of semantic associations over a group of words and text combinations.

Online version