Inspired by this, we propose AdaL, with a transformation on the original gradient.
However, many existing works can not be widely used because of the constraints of functional form of generative models or the sensitivity to hyperparameters.
In this paper, based on in-situ TBM operational data, we use the machine-learning (ML) methods to build the real-time forecast models for TBM load parameters, which can instantaneously provide the future values of the TBM load parameters as long as the current data are collected.
With the newly introduced DAL, we achieve superior detection performance for arbitrary-oriented objects with only a few horizontal preset anchors.
Ranked #1 on 2D Object Detection on DOTA (using extra training data)
Based on our theoretical and empirical analysis, we establish a universal theoretical framework of GCN from an optimization perspective and derive a novel convolutional kernel named GCN+ which has lower parameter amount while relieving the over-smoothing inherently.
In addition, to alleviate KL-vanishing problem in SGRNN, a simple and interpretable structure is proposed based on the lower bound of KL-divergence.
We propose a novel Ensemble-Learning for Missing Value (ELMV) framework, which introduces an effective approach to construct multiple subsets of the original EHR data with a much lower missing rate, as well as mobilizing a dedicated support set for the ensemble learning in the purpose of reducing the bias caused by substantial missing values.
This paper studies cooperative tracking problem of heterogeneous Euler-Lagrange systems with an uncertain leader, with emphasis on simultaneous adaptive estimation of the state and parameters of the leader node.