Por Alberto Bressan (Penn State University).
Por Daniel Barlet (Inst. Élie Cartan, Lorraine).
Abstract: We shall explain how the classical intersection theory of cycles in a complex manifold is generalized to an ambient nearly smooth complex space. A key point is the local moving lemma for cycles in a complex manifold. The new phenomenon is the fact that the intersection multiplicity of two integral cycles may be a rational not integral number in this context.
Por Gabriele Pulcini (FCT, Universidade Nova de Lisboa).
Por Paulo Amorim (Instituto de Matemática - Universidade Federal do Rio de Janeiro).
O que fazem e o que pensam alguns membros da comunidade de Ciências? O Dictum et factum de fevereiro de 2018 é com João Martins, técnico superior do Departamento de Física de Ciências.
Pigeons do not jump high / Using o-minimality to compute lower bounds on sample complexity of neural networks (part 2)
Pigeons do not jump high 15h00
Por Ludovic Patey (Institut Camille Jordain, Lyon).
Por Carlos Florentino (Faculdade de Ciências da Universidade de Lisboa).
Por Inês Martins Rodrigues (aluna de doutoramento da FCUL).
Abstract: The Robinson-Schensted correspondence, introduced by Schensted (1961) in its most well-known form, presents a bijective correspondence between permutations and pairs of standard Young tableaux of the same shape. Knuth (1970) presented a generalization, the RSK correspondence, for semistandard Young tableaux.
Por Alexandre Baraviera (Instituto de Matemática e Estatística - Universidade Federal do Rio Grande do Sul).
Por Alex Usvyatsov (Universidade de Lisboa, CMAF-CIO).
Abstract: I will discuss the concept of sample complexity in statistical learning theory. Then I will show how definability of many hypothesis classes (for example, essentially all artificial neural networks used in practice) in o-minimal structures, helps to compute tighter lower bounds on sample complexity for these hypothesis classes.
