PLN – Módulo I: Processamento de Texto nos dias de hoje: Tarefas, Métodos e Recursos Gustavo Henrique Paetzold Responsável: Sandra Aluisio Resumo: Em tarefas de Processamento de Texto, objetiva-se explorar, interpretar, manipular ou até gerar segmentos de texto. A forma como estas tarefas são endereçadas evoluiu muito recentemente, e os principais responsáveis…
Responsável: Alneu Lopes Abstract: The analysis of large volumes of textual data requires the use of text-mining approaches. They enable to discover knowledge useful for experts of different domains (e.g. Epidemiology, Humanities, etc.). The course will present some approaches in order to deal with heterogenous textual data by focusing on the…
Responsável: Alneu Lopes Abstract: Recent improvements in positioning technology have led to a much wider availability of massive moving object data. A crucial task is to find the moving objects such as people, animals, vehicles that travel together. In common, these object sets are called object movement patterns. Many approaches…
Responsável: Agma Traina e Caetano Traina Jr. Abstract: The Big Data era is upon us: data are being generated, collected and analyzed at an unprecedented scale, and data-driven decision making is sweeping through all aspects of society. Since the value of data explodes when it can be linked and fused with other…
Responsáveis: Robson Leonardo Ferreira Cordeiro e José Fernando Rodrigues Junior Resumo: Apresentação de fundamento em BigData, que poderia abordar a teoria do porque o Google adotou a troca dos paradigmas tradicionais de software que são “Fetch Architecture” (pilha tradicional storage + db relacional + app server) e “Schema on Write” para lidar em BigData usando “Locality strategy” (aplicação vai até onde o dado…
Lecture Summary: Agriculture is at a crossroads where gains from traditional sources are predicted to level off by 2050. Consequently agricultural researchers are beginning to use machine learning techniques to allow farmers and farm managers to make better decisions. These better decisions lead to increased yields, and reduced production costs. This…
I will discuss in this talk the importance of the global pooling operation in deep convolutional architectures. Several recent approaches only differ in the way (how) and place (where) it is achieved inside the network. I will detail several block combinations in deep architectures to achieve global pooling, and compare different…
The advent of large scale online social services coupled with the dissemination of affordable GPS enabled smartphones resulted in the accumulation of massive amounts of data documenting our individual and social behavior. Using large data sets from source such as Twitter, Wikipedia, Google Books and others we will present several…
IBM Master Inventor, researcher at IBM, and associated collaborator at Federal University of ABC (UFABC). PhD and MSc degrees in Computer Science from University of Campinas (UNICAMP), 2012 and 2009, respectively. BSc degree in Computer Science from Presbyterian University Mackenzie (2006). Was webmaster of Folha Online (www.folha.com.br) from 2002 to…
Biometric authentication verifies the identity of individuals based on what they are. However, biometric authentication systems are error prone and can reject genuine individuals or accept impostors. Researchers on biometric authentication quantify the quality of their algorithm by benchmarking it several databases. However, although the standard evaluation metrics state the…