These days it would not be an exaggeration to say that we live in a world where AI applications are taking over. What is sure that they are impressing the public more and more. Couple years ago, GANs impressed people for creating images which do not exist in reality. The culmination was Dalle2 project which could create a new image from any description one gave to it. With the developments in the Natural Language Understanding now Chatbots can understand and answer questions one asks. Recently, ChatGPT proved it to everyone. Creating new, before non-existing images can be impressing. However, it is a Chatbot, which fascinates human beings the most. Can an algorithm think, communicate, and talk or even may be feel like us? What are the technologies behind it? In this talk I would like to shed a light to the development of Natural Language Technologies starting from the early applications up to the modern deep learning algorithms. I will give a direct intuition and explanation on how algorithms learn languages. Algorithms like Word2Vec and Transformers are not only going to be explained, but I will try to put everything into the landscape of existing technologies, from mathematical and topological point of view.
Dr. Joshgun Sirajzade is a post-doctoral researcher within the Faculty of Science, Technology and Medicine at the University of Luxembourg.
The Machine Learning Seminar is a regular weekly seminar series aiming to harbour presentations of fundamental and methodological advances in data science and machine learning as well as to discuss application areas presented by domain specialists. The uniqueness of the seminar series lies in its attempt to extract common denominators between domain areas and to challenge existing methodologies. The focus is thus on theory and applications to a wide range of domains, including Computational Physics and Engineering, Computational Biology and Life Sciences, Computational Behavioural and Social Sciences. More information about the ML Seminar, together with video recordings from past meetings you will find here: https://legato-team.eu/seminars/
To register please send a mail to Dr. Jakub Lengiewicz.