A new artificial intelligence project at ELTE
Neural network – based approximation of Dirichlet-to-Neumann maps are shown, as part of our major project in machine learning.
Read moreAuthor: zempleni
Lightweight diacritic restoration for V4 languages
Diacritics restoration became a ubiquitous task in the Latin-alphabet-based English-dominated Internet language environment. We showcase a small footprint 1D convolution-based solution, running in a web browser, which surpassed the performance of similarly sized models. Many languages have alphabets where some characters are derived from other characters using diacritical marks. The […]
Read moreEstimation and simulation of fractional Ornstein-Uhlenbeck processes, using deep neural networks
There is now a great deal of interest in parameter estimation of Ornstein-Uhlenbeck processes in finance because of its modelling capability (see e.g. [1]). That is why we investigated prediction of the unknown parameters with neural networks in the hope that we will obtain more accurate estimators than the ones […]
Read moreMathematics Expert in Data Analytics and Machine Learning
A new program has started for graduates at Eötvös Loránd University: This program is for those, who want to be among the winners of the socio-economic transformations generated by artificial intelligence. It is well-known than those can make the most of the possibilities offered by artificial intelligence who well understand […]
Read moreThe development of projects at Eötvös Loránd University, Budapest
What are the key issues in an MSc in applied maths? Of course the applications and the maths! But the order (and even more the emphasis) matters. In Budapest we had a traditionally strong theoretical mathematics education and when the new direction of Applied Maths was launched in the 1990s,
Read more
You must be logged in to post a comment.