Modern approaches, using ultra-precise neural nets, make it possible to achieve excellent results when working with good-quality source data, but a lot of quality is lost when the data is noisy (out of focus, blurred, or afflicted with other kinds of noise).
We have created our own recognition algorithms for these noisy images, employing a mathematical toolkit based on Markov chains and random metrical spaces. Unlike the majority of machine learning methods, for us a high dimensionality of the feature space is not a difficulty (the "curse of dimensionality") but rather an opportunity to obtain new results.
For the well-known MNIST database of handwritten numerals we create a software system that can retain a low error rate (20% or less) even with intensive noise (50-60%) in the source data. The next step is integration with other platforms to work with real images of a low quality.
Spirit of Gadget is a lookalike platform for clustering smartphone users based on behavioral features, and producing app recommendations.
Spirit of Gadget is an innovative approach that allows each person to benefit from the experience of others.
In 2012 1.68 million new cases of breast cancer were registered, 522000 patients with this diagnosis died . Lung cancer is the most common cause of cancer-related death among men and second most common among women . Overall, 17.4% of people in the United States diagnosed with lung cancer survive five years after the diagnosis .
An early detection plays important role in cancer treatment. CT and X-ray screening “by hand” is a complicated and diligent procedure requiring lots of highly qualified specialists's work hours.
Nowadays deep machine-learning technologies, based primarily on convolutional neural networks, are rapidly evolving, thus significantly simplifying and speeding up diagnostics. A potential of such technologies in the early-stage cancer diagnostics is yet to be studied. In this regard cooperation with world class specialists to "teach" neural networks is playing a key role.
DataSmart continuously studies and implements brand new machine learning technologies cooperating with some of the leading oncologists of Saint-Petersburg. Mammograms and additional medical data are used in combination. Prior results of this project will soon be released.
Saint Petersburg, Russia, 20, Nalichnaya avenue