In this paper, the modified gravity, which is characterized by factor $\mu$ in linear matter density perturbation theory, reconstructed a completely data-driven and model-independent way via Gaussian process using currently available cosmic observations, consist Pantheon+ SNe Ia samples, observed Hubble parameter $H(z)$ redshift space distortion $f\sigma_8(z)$ data points. The results suggest t...

The geometric structure of an optimization landscape is argued to be fundamentally important support the success deep neural network learning. A direct computation beyond two layers hard. Therefore, capture global view landscape, interpretable model network-parameter (or weight) space must established. However, lacking so far. Furthermore, it remains unknown what looks like for networks binary ...