Search by tag «Algorithms» 33 results

• "In English, Please": De-Jargonizer Helps Make Science Accessible

  Israeli scientists have developed software that can analyze a scientific article’s level of comprehensibility. The algorithm, named De-Jargonizer, separates words into three categories according to their frequency of use and, using a simple formula, determines how accessible the text will be to a wider audience. Having tested their software on articles from PLOS ONE, the scientists learned that the abstracts of some articles can consist of rare scientific terms by up to 27 percent. Developers hope that their program will help adapt texts to be more accessible to a majority of people.

  21.08.2017

• ITMO Students in Singapore: How to Please Customers by Analyzing Their Social Media

  In future, social networks could make advertisers’ work much easier. Big Data analysis algorithms can already figure out the ins and outs of a customer’s personality. They can be used to track negative reviews, determine the customers’ desires, identify their psychological type and tailor advertisements according to each customer’s data. A group of Master’s Degree students from the Computer Technologies Department have studied this topic at the National University of Singapore. They have told us about their research and the pros and cons of living in a city state. 

  21.06.2017

• Teaching the Machine: The Prospects of Neural Networks

  A diagnostician bot that can tell you which doctor you should go to, or a system that can define the winner of a beauty contest all by itself — such things are no longer traits of a science-fiction novel, but descriptions of real programs. Each is based on neural networks, which progress in analyzing texts and recognizing items or faces with every passing day. One can even train the network to find a personal Pokemon for everyone, like Ludmila Kornilova, a student from ITMO University, did. In an interview to ITMO.NEWS, she shared about her projects in machine learning, and whether a machine can discern right from wrong.

  22.02.2017