Abstract: A carbon sink enhancement method based on oyster-Undaria pinnatifida integrated aquaculture is performed as follows. Oysters with similar size and appearance are selected, washed and evenly spread onto a bottom of an incubator, to which 5-15° C. seawater is added. A rope is fixed on an upper side wall of the incubator. Undaria pinnatifida seedlings are spacedly clamped on the rope for spaced hanging culture. A wet weight ratio of the oyster to the Undaria pinnatifida seedlings is 6-8:1. The incubator is placed under sunlight for mixed culture, during which the incubator remains closed without water replacement. The oysters or the Undaria pinnatifida seedlings are taken out when the oyster reaches a meat yield of 10% or more or a length of the Undaria pinnatifida seedlings is larger than 100 cm. Seawater samples are collected to detect water quality parameters for carbon sink assessment.

Abstract: A computer implemented method obtains neural network-based model base model weight matrices for each of multiple neural network layers. First low-rank factorization matrices are added to corresponding base model weight matrices to form a first domain model. The low-rank factorization matrices are treated as trainable parameters. The first domain model is trained with first domain specific training data without modifying base model weight matrices.

Abstract: Systems and method are provided that are directed to tuning a hyperparameter associated with a small neural network model and transferring the hyperparameter to a large neural network model. At least one neural network model may be received along with a request for one or more tuned hyperparameters. Prior to scaling the large neural network, the large neural network is parameterized in accordance with a parameterizing schemed. The large neural network is then scaled and reduced in size such that a hyperparameter tuning process may be performed. A tuned hyperparameter may then be provided to a requestor such that the hyperparameter can be directly input into the large neural network. By tuning a hyper parameter using a small neural network, significant computation cycles and energy may be saved.