Zobrazeno 1 - 10
of 114
pro vyhledávání: '"Schizas, Ioannis"'
Equipping graph neural networks with a convolution operation defined in terms of a cellular sheaf offers advantages for learning expressive representations of heterophilic graph data. The most flexible approach to constructing the sheaf is to learn i
Externí odkaz:
http://arxiv.org/abs/2410.09590
Mammals navigate novel environments and exhibit resilience to sparse environmental sensory cues via place and grid cells, which encode position in space. While the efficiency of grid cell coding has been extensively studied, the computational role of
Externí odkaz:
http://arxiv.org/abs/2407.06195
A common technique for ameliorating the computational costs of running large neural models is sparsification, or the removal of neural connections during training. Sparse models are capable of maintaining the high accuracy of state of the art models,
Externí odkaz:
http://arxiv.org/abs/2406.06290
Publikováno v:
In Pattern Recognition February 2025 158
Autor:
Schizas, Ioannis D.
A novel approach is put forth that utilizes data similarity, quantified on a graph, to improve upon the reconstruction performance of principal component analysis. The tasks of data dimensionality reduction and reconstruction are formulated as graph
Externí odkaz:
http://arxiv.org/abs/1809.09266
Dual-fisheye lens cameras are becoming popular for 360-degree video capture, especially for User-generated content (UGC), since they are affordable and portable. Images generated by the dual-fisheye cameras have limited overlap and hence require non-
Externí odkaz:
http://arxiv.org/abs/1708.05922
This chapter deals with decentralized learning algorithms for in-network processing of graph-valued data. A generic learning problem is formulated and recast into a separable form, which is iteratively minimized using the alternating-direction method
Externí odkaz:
http://arxiv.org/abs/1503.08855
Autor:
Malhotra, Akshay, Schizas, Ioannis D.
Publikováno v:
In Pattern Recognition December 2020 108
Sparsity in the eigenvectors of signal covariance matrices is exploited in this paper for compression and denoising. Dimensionality reduction (DR) and quantization modules present in many practical compression schemes such as transform codecs, are de
Externí odkaz:
http://arxiv.org/abs/1201.3599
Publikováno v:
In Computational Statistics and Data Analysis January 2018 117:90-108