• Adversarial autoencoders with constant-curvature latent manifolds 

  Grattarola, D; Livi, L; Alippi, C (Elsevier, 22 May 2019)

  Constant-curvature Riemannian manifolds (CCMs)have been shown to be ideal embedding spaces in many application domains, as their non-Euclidean geometry can naturally account for some relevant properties of data, like ...

• Deep divergence-based approach to clustering 

  Kampffmeyer, M; Løkse, S; Bianchi, FM; et al. (Elsevier, 8 February 2019)

  A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function. As opposed to supervised ...

• Learning to decompose: a paradigm for decomposition-based multiobjective optimization 

  Wu, M; Li, K; Kwong, S; et al. (Institute of Electrical and Electronics Engineers, 1 June 2019)

  The decomposition-based evolutionary multiobjective optimization (EMO) algorithm has become an increasingly popular choice for a posteriori multiobjective optimization. However, recent studies have shown that their performance ...

• Entropy in network community as an indicator of language structure in emoji usage: A twitter study across various thematic datasets 

  Hartman, R; Seyednezhad, SMM; Pinheiro, D; et al. (Springer, 2 December 2018)

  Emojis are emerging as an alternative way to interact and communicate online, and their large-scale adoption has the potential to reveal distinct patterns of human communication and social interactions. In this work, we ...

• An approach for thematic relevance analysis applied to textual contributions in discussion forums 

  MacHado, CJR; MacIel, AMA; Rodrigues, RL; et al. (IGI Global, 1 January 2019)

  Discussion forums in learning management systems (LMS) have been shown to promote student interaction and contribute to the collaborative practice in the teaching-learning process. By evaluating the postings, teachers can ...

View more