The purpose of this article is to describe a technique for secondary reconstruction of traumatic orbital wall defects using titanium implants that act as three-dimensional (3D) puzzle pieces. We present three cases of large defect reconstruction using implants produced by Xilloc Medical B.V. (Maastricht, the Netherlands) with a 3D printer manufactured by LayerWise (3D Systems; Heverlee, Belgium...

We present and test a new hybrid numerical method for simulating layerwise-twodimensional geophysical flows. The method radically extends the original ContourAdvective Semi-Lagrangian (CASL) algorithm (Dritschel & Ambaum, 1997) by combining three computational elements for the advection of general tracers (e.g. potential vorticity, water vapor, etc.): (1) a pseudo-spectral method for large scal...

This paper proposes a classifier called deep adaptive networks (DAN) based on deep belief networks (DBN) for visual data classification. First, we construct a directed deep belief nets by using a set of Restricted Boltzmann Machines (RBM) and a Gaussian RBM via greedy and layerwise unsupervised learning. Then, we refine the parameter space of the deep architecture to adapt the classification re...

We present a novel layerwise optimization algorithm for the learning objective of Piecewise-Linear Convolutional Neural Networks (PL-CNNs), a large class of convolutional neural networks. Specifically, PL-CNNs employ piecewise linear non-linearities such as the commonly used ReLU and max-pool, and an SVM classifier as the final layer. The key observation of our approach is that the problem corr...

The North Atlantic ocean is key to climate through its role in heat transport and storage. Climate models suggest that the circulation weakening but physical drivers of this change are poorly constrained. Here, root mechanisms revealed with explicitly transparent machine learning (ML) method Tracking global Heating Ocean Regimes (THOR). Addressing fundamental question existence dynamical cohere...