Towards more dynamic and efficient Machine Learning pipelines
O Departamento de Engenharia Informática (DEI) do Instituto Superior de Engenharia do Porto (ISEP), numa iniciativa conjunta com o Mestrado em Engenharia de Inteligência Artificial (MEIA), convida à participação em mais uma AI Master Class, desta vez sobre o tema "Towards more dynamic and efficient Machine Learning pipelines", que terá lugar no dia 13 de dezembro, pelas 19h00, no ISEP.
O evento será presencial, na sala B202.
At a time in which machine learning algorithms have never been so powerful, and when we have unprecedented access to computational resources, it feels rather contradictory that we still face some of the toughest technical and scientific challenges of the field to date. This can be explained by several factors. Data are now dynamic, streaming rather than batch, with their statistical properties changing over time. So, models must be updated regularly. But data are also growing, so training new models takes more time, often too much. And how to pick the best model/configuration, in a time in which the possibilities are virtually infinite, and in which environmental concerns and legislation push towards a more judicious use of computational resources? These challenges are the starting point for this Masterclass, in which different solutions, developed in the context of several funded research projects, will be presented. Specifically, we will discuss how approaches such as meta-learning or optimization can be used to improve current machine learning pipelines.
- Data e local
- Informação Adicional
Davide Carneiro is an Adjunct Professor at the School of Management and Technology, of the Polytechnic Institute of Porto. He is also an integrated member of the CIICESI Research Centre, of the Polytechnic Institute of Porto, and collaborates with the INESC TEC centre. He holds a PhD from a joint Doctoral Programme in Computer Science of three top Portuguese Universities (MAP-i Programme – Minho, Aveiro and Porto). He develops scientific research in the field of Artificial Intelligence, touching topics such as Machine Learning (including distributed and streaming Machine Learning), Meta-Learning and AI Ethics. The application areas of his research include Healthcare and Wellbeing, Online Conflict Resolution and Fraud Detection. In the past, Davide has coordinated or participated in several national and international funded research projects in these fields. He is currently the scientific coordinator of the NEURAT project (NORTE-01-0247-FEDER-039900), the institutional coordinator of the EU-funded EJUST ODR Scheme project (JUST-2021-EJUSTICE, 101046468) and the Principal Investigator of the FCT-funded projects CEDEs (EXPL/CCI- COM/0706/2021) and xAIDMLS (CPCA-IAC/AV/475278/2022). He is also currently participating in the FACILITATE-AI project. He is the author of more than 140 publications in his fields of interest, including one authored book, four edited books, and over one 130 book chapters, journal papers and conference and workshop papers. He is also the co-founder and CRO of AnyBrain, a Portuguese startup in the field of Human Computer Interaction. The company develops software for fatigue detection in office environments (https://performetric.net/), performance assessment in eSports (https://performetric.gg/), and user identification and cheat detection (https://anybrain.gg/).
Local: O evento será presencial, na sala B202
O evento não necessita de inscrição prévia.
Para mais informações: firstname.lastname@example.org
Organização: Esta palestra é organizada pelo QTDEI em colaboração com o Mestrado em Engenharia de Inteligência Artificial (MEIA) do Instituto Superior de Engenharia do Porto (ISEP).