Abstract: In this paper, we study autonomous landing scene recognition with knowledge transfer for drones. Considering the difficulties in aerial remote sensing, especially that some scenes are ...

As modern computing becomes limited by energy consumption, there is growing interest in physical computing paradigms that can operate closer to fundamental thermodynamic limits. Thermodynamic ...

The architecture of our RDLUF with $K$ stages (iterations). RDLGD and PM denote the Residual Degradation Learning Gradient Descent module and the Proximal Mapping ...

Modern, large-scale scientific datasets with tens of thousands of variables and millions of samples can accelerate scientific discovery by revealing underlying structure in data based on dependence ...

A critical challenge in neuromorphic computing is to present computationally efficient algorithms of learning. When implementing gradient-based learning, error ...

Tree boosting has empirically proven to be efficient for predictive mining for both classification and regression. For many years, MART (multiple additive regression trees) has been the tree boosting ...

In this paper we study the problem of minimizing the average of a large number of smooth convex loss functions. We propose a new method, S2GD (Semi-Stochastic Gradient Descent), which runs for one or ...