Category: [rede.APPIA]

A [rede.APPIA] é a lista de distribuição de correio electrónico da APPIA, com o objectivo de divulgar notícias de interesse para a comunidade científica da Inteligência Artificial, disponível através do endereço rede [at] appia [ponto] pt.

[rede.APPIA] DaSSWeb – Data Science and Statistics Webinar – 5 November – Peter Flach – Explainable Artificial Intelligence, Explained

MC
DaSSWeb – Data Science and Statistics Webinar

 

Tuesday, 5 November, 14:30 (GMT)

 

Speaker

Peter Flach

School of Computer Science, University of Bristol, UK


Title

Explainable Artificial Intelligence, Explained

 

Zoom link

Abstract

Explainable Artificial Intelligence (XAI for short) aims at giving insight in the behaviour of AI models in general
and machine learning models in particular. In this talk I will give an overview of this growing field,
using some recent results from my group as examples. These include explainability for time series (LIMEsegment);
actionable counterfactuals (FACE); explainability fact sheets; as well as the fat-forensics.org toolkit for evaluating
Fairness, Accountability and Transparency of AI systems. Finally, I will discuss the importance of properly
treating probabilities in feature attribution methods such as LIME and SHAP through log-linear models,
and extensions to multi-class settings.

 

More information at

https://dassweb.fep.up.pt/

pdf icon DaSSWeb-Peter-Flach-5Nov2024.pdf

[rede.APPIA] FEUP | Permanent Position – Assistant Researcher | NLP and Language Models

MC
A permanent research position for FEUP / LIACC is open in the domain of intelligent systems, artificial intelligence, computational learning and natural language processing, with an emphasis on the field of large language models.
Applications are open until 20 Nov 2024.
More information:

[rede.APPIA] Thematic Issue on Urban Computing and Mobility Pattern Analysis – Journal of Ambient Intelligence and Smart Environments [JAISE

MC
Dear colleagues,

Please consider submitting a contribution to this thematic issue or share it with your contacts who might be interested:
Submission before November 1, 2024

Urbanization has modernized life, but it has also caused problems such as traffic congestion, energy consumption, and pollution. Urban computing aims to solve these problems using data generated by the city or opportunistic data obtained through crowdsourcing (e.g., traffic flow, human mobility, geospatial data). It integrates urban sensing, data management, analysis and service provision to continuously improve urban life, urban operations and the environment. Urban computing is interdisciplinary, merging computer science with fields such as civil engineering (e.g., transportation engineering), and sociology.

Smart environments are expanding from artefacts to smart cities, encompassing various urban activities. To understand and optimize urban mobility and human behaviour, machine learning models have been proposed. Smart mobility, or smart transport, is a vital component of smart cities, which use information and communications technologies (ICT) to reduce road accidents, energy consumption, CO2 emissions, noise and congestion. It represents a revolution in intelligent transport systems (ITS), intending to reduce traffic-related greenhouse gas emissions and economic losses due to congestion. Urban Computing covers a wide range of topics, including smart city applications, urban sensing, and spatial analytics. This thematic issue invites contributions focused on innovative methodologies for analyzing and predicting mobility patterns using diverse data sources like GPS traces, mobile phone data, transit logs, and social media feeds.

Potential topics of interest include but are not limited to:

Urban Computing
Mobility Pattern Analysis
Intelligent Transport Systems
Ubiquitous Transport Technologies and Ambient Intelligence
Volunteered Geographic Information
Behaviour Modelling
Smart Mobility in Smart Cities
Machine Learning in Mobility
Opportunistic Data Crowdsourcing
Emerging Mobility Services
On-Demand Shared Mobility Services
Emerging Mobility Technologies

Guest Editors
Ana Alves
Filipe Rodrigues
Merkebe Getachew Demissie

Ana Alves

PhD in Computer Science
CISUC -Centre for Informatics and Systems of the University of Coimbra
ana@dei.uc.pt
http://eden.dei.uc.pt/~ana

[rede.APPIA] CFP: Journal Track with ECML PKDD 2025 at Porto, Portugal

MC
We invite submissions of high-quality manuscripts reporting relevant research studies on all topics related to machine learning, knowledge discovery, and data mining for the journal track of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD) 2025. The journal track is implemented in partnership with the Machine Learning Journal and the Data Mining and Knowledge Discovery Journal. The conference provides an international forum to discuss the latest high-quality research results in all areas related to machine learning, data mining, and knowledge discovery. The complete CFP can be found at ecmlpkdd.org/2025/submissions-journal-track/.
———————- Time scale ———————- The journal track allows continuous submissions from October 2024 to February 2025. Papers will be processed and sent out for review after each of the following three cutoff dates:
October 11, 2024 December 13, 2024 February 14, 2025
The deadline on these dates is 23:59, Anywhere on Earth (AoE). The reviewing process is single-blind.
———————- Submission procedure ———————- To submit to this track, authors have to make a journal submission to the CMT site (link cmt3.research.microsoft.com/ECMLPKDDJT2025/Submission/Index). They must submit the title and abstract, add the author names, choose the areas related to the paper, fill out an information sheet, and indicate which of the two journals the paper is intended for. The full paper in pdf format, following the Springer templates, must also be submitted to the CMT system. Please note that no paper can be submitted to both journals. It is highly recommended that submitted papers do not exceed 20 pages, including references. Unlimited appendices may accompany every paper. Manuscripts submitted to the Journal Track that receive the final acceptance decision by July 15, 2025, will be presented at ECML-PKDD 2025 in Porto.
———————- Contact ———————- For further information, please contact the email: ecml-pkdd-2025-journal-track-chairs@googlegroups.com
———————- Journal Track Chairs ———————- Ana Carolina Lorena, Aeronautics Institute of Technology, Brazil Concha Bielza, Universidad Politécnica de Madrid, Spain Longbing Cao, University of Technology Sydney, Australia Arlindo Oliveira, Instituto Superior Técnico, Portugal
Carlos Ferreira
ISEP | Instituto Superior de Engenharia do Porto Rua Dr. António Bernardino de Almeida, 431 4249-015 Porto – PORTUGAL tel. +351 228 340 500 | fax +351 228 321 159 mail@isep.ipp.pt | www.isep.ipp.pt
— Esta mensagem foi enviada para a rede APPIA, que engloba os associados da APPIA. Se desejar deixar de receber este tipo de mensagens, p.f. envie um email para appia [at] appia [ponto] pt

Vencedor do Concurso Melhor Tese de Doutoramento

appiaAdmin

Parabéns ao Vencedor do Prémio de Melhor Tese de Doutoramento 2023

Temos o prazer de anunciar que o Prémio de Melhor Tese de Doutoramento de 2023 da APPIA, foi entregue no Jantar da conferência do EPIA 2024. O vencedor foi o Miguel Vasco do Instituto Superior Técnico, Universidade de Lisboa, Portugal.

Título da Tese:

Multimodal Representation Learning for Agent Perception and Agency

Orientadores:

Prof. Ana Paiva e Prof. Francisco S. Melo

Parabéns mais uma vez por esta conquista merecida!

[rede.APPIA] THIS ONE ! – DaSSWeb – Data Science and Statistics Webinar – 15 October – Gilbert Saporta – Sparse Correspondence Analysis for Contingency Tables

MC
The previous e-mail message was wrong, we apologize, please discard it.
++++++++++++++++++++++++++++++++++++++
DaSSWeb – Data Science and Statistics Webinar

 

Tuesday, 15 October, 14:30 (WEST)

 

Speaker

Gilbert Saporta

CNAM, Paris, France


Title

Sparse Correspondence Analysis for Contingency Tables

 

Zoom link

Abstract

We propose sparse variants of correspondence analysis (CA) for large contingency tables like documents-terms matrices used in text mining. By seeking to obtain many zero coefficients, sparse CA remedies to the difficulty of interpreting CA results when the size of the table is large. Since CA is a double weighted PCA (for rows and columns) or a weighted generalized SVD, we adapt known sparse versions of these methods with specific developments to obtain orthogonal solutions and to tune the sparseness parameters. We distinguish two cases depending on whether sparseness is asked for both rows and columns, or only for one set.

 

More information at

[rede.APPIA] CFP [Extended Deadline is October 13]: DATA STREAMS TRACK – ACM SAC 2025

MC
===========================
ACM SAC 2025 Data Streams track
Due to several requests, the deadline has been extended by 2 weeks: abifet.github.io/SAC2025/
Paper Submission: October 13, 2024 (Extended Deadline)
Please submit your contribution via SAC 2025 Webpage: easychair.org/conferences/?conf=sac-2025
===========================
Carlos Ferreira
ISEP | Instituto Superior de Engenharia do Porto Rua Dr. António Bernardino de Almeida, 431 4249-015 Porto – PORTUGAL tel. +351 228 340 500 | fax +351 228 321 159 mail@isep.ipp.pt | www.isep.ipp.pt
— Esta mensagem foi enviada para a rede APPIA, que engloba os associados da APPIA. Se desejar deixar de receber este tipo de mensagens, p.f. envie um email para appia [at] appia [ponto] pt