We’ve begun 2018 with another non-trivial and interesting topic connected with human-computer interaction – Recognition Morning@Lohika. This time, with our old friend Mykola Maksymenko, and two new friends – Matvii Kovtun, Junior Data Scientist @ Eleks, and Oles Dobosevych, Deputy Dean, Faculty of Applied Sciences @ UCU. The event took place this January 27, at Lohika Lviv Office.
Researcher focused on applied Machine Learning, i.e. bio-metric applications, affective computing, signal processing. Holds a PhD in theoretical physics and worked as a researcher in Germany and Israel (Max-Planck Society and Weizmann Institute of Science), developing theory and algorithms for various complex-systems problems spanning from infection propagation in social networks to design of novel quantum states and magnetic materials. His current research touches statistical physics of neural networks and application of tensor network algorithms in machine learning.
How can machine understand Emotions?
Giving machines the power to recognize human emotions is on agenda of many research groups in the world. The technology allows novel fields of human-computer interactions, dubbed Affective Computing, as well as entirely new possibilities for businesses to interact with their customers.
The true Emotion Recognition is far more complex than basic recognition of facial expressions. In practice, it requires acquiring of multi-mode biosignals and behavioral data and a good deal of signal processing and feature engineering game.
Matvii Kovtun, Junior Data Scientist @ Eleks
Matvii Kovtun is Junior Data Scientist at ELEKS and 3rd year student at Faculty of Applied Sciences @ Ukrainian Catholic University. His professional interests are machine learning and computer vision.
Oles Dobosevych, Deputy Dean, Faculty of Applied Sciences @ UCU
Oles Dobosevych is Deputy Dean, Faculty of Applied Science @ Ukrainian Catholic University. Oles has more than seven years of experience in IT industry which varies from web development to personal analytics. Currently, Oles is running his own business, completing Ph.D. thesis in functional analysis and teaching at Ukrainian Catholic University. His professional interests are machine learning and functional analysis.
MNIST Ukrainian Style
Modified National Institute of Standards and Technology (MNIST) dataset of handwritten digits is de facto standard for training various image processing systems. It is popular, high-quality and obviously well-studied. Most of us took their first steps in machine learning using it. But its applicability is clearly limited to handwritten digits.
During this talk, we discussed collected MNIST-style dataset of handwritten Ukrainian characters Matvii and Oles explained how ML algorithms may save paper, time and money in Ukrainian realities.