Text Classification using Deep Learning
The amount of unstructured data is growing significantly. One type of such kind of data is text data. In presentation the most recent techniques of text documents classification will be compared in order to minimize error level.
In the first part I will talk about Information Retrieval. I will cover mostly Algebraic models, which create vector representation of a text documents. Such output is the most suitable for Machine Learning methods.
In the second part I will do comparison of document classification using Machine Learning and Deep Learning approaches on different data sets.
Data Scientist, GE
Valentin Mikhaylenko is Data Scientist and Solution Architect is GE Healthcare. Prior to that, Valentin was software developer in automated stock trading company (High Frequency Trading) for 7 years and Data Scientist in Natural Language Processing startup for 2 years. He graduated summa cum laude from ITMO University (Saint Petersburg, Russia) with a MSc in Applied Mathematics and Informatics. Also Valentin graduated from Borland Academy (supported by Yandex and Jetbrains).