Speaker: Raul Ian Sosa (Co-founder of NeuralWave technologies & Department of Physics, FSTM, University of Luxembourg)
Title: Understanding Attention for Modern AI.
Time: Wednesday, 2023.10.04, 10:00 a.m. (CET)
Place: fully virtual (contact Jakub Lengiewicz to register)
Format: 30 min. presentation + 30 min. discussion
Abstract: In our talk, we will explore the attention mechanism, a pivotal concept in artificial intelligence. We will demystify what it is, explain its unique ability to focus on specific elements in a sequence, and how it mirrors human cognitive processes. We will discuss its transformative role in AI, from its inception to how it is now a crucial part of the development of transformer models. By the end of this talk, we will have a clear understanding of the attention mechanism’s importance and many of its practical applications.
Ian is a physicist, A.I. developer, and entrepreneur. He completed his Bachelor’s and Master’s degrees in Statistical Physics at the Balseiro Institute, Argentina, in 2020 and 2021 respectively. In 2022, he relocated to Luxembourg to pursue a PhD in the Department of Physics and Materials Science at UniLu, focusing on modeling the emergence of quantum mechanical effects in macroscopic systems. Concurrently, he co-founded an A.I. voice synthesis company, NeuralWave, which develops tools for voice generation and voice cloning to reduce costs in entertainment productions and enhance company-customer interactions..
The aim of the Machine Learning Seminar series is to host presentations on 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. Therefore, the focus is on theory and applications to a wide range of domains, including Computational Physics and Engineering, Computational Biology and Life Sciences, and Computational Behavioural and Social Sciences.
The seminar aims to bring together young and experienced researchers from various disciplines to exchange ideas on Machine Learning techniques. It is currently affiliated with the University of Luxembourg and its DSSE doctoral programme, and is run in partnership with the DTU DRIVEN PRIDE project, funded by the FNR, and the widening participation DRIVEN project, funded by H2020. The seminar also welcomes talks by researchers from a wider collaborative network, including but not limited to early-stage researchers in RAINBOW ITN, as well as current and incoming individual Marie Skłodowska-Curie fellows.
The usual format is as follows: a short presentation (20-30 minutes) followed by a longer discussion (30-40 minutes). The usual time is Wednesdays at 10:00 a.m. (CET). If you are interested in joining, please contact Jakub Lengiewicz.
See https://www.jlengineer.eu/ml-seminar/ .
source
