Learn More
While models of fine-grained recognition have made great progress in recent years, little work has focused on a key ingredient of making recognition work: data. We use publicly available, noisy data sources to train generic models which vastly improve upon state-of-the-art on finegrained benchmarks. First, we present an active learning system using(More)
Nitinol (nickel–titanium) alloys exhibit a combination of properties which make these alloys particularly suited for self-expanding stents. Some of these properties cannot be found in engineering materials used for stents presently. This article explains the fundamental mechanism of shape memory and superelasticity, and how they relate to the characteristic(More)
The purpose of this paper is to contrast the performance of self-expanding and balloon-expandable stents. While both approaches to stenting have proven to be successful in treating a wide range of vascular disease, there are significant differences in the philosophy behind and properties of the two types of stents. Many of these differences, such as(More)
Nitinol alloys (Nitinol) exhibit a dramatically enhanced elasticity, known as "superelasticity", which is becoming integral to the design of a variety of new medical products. Elasticity is the most apparent of the advantages afforded by this material, but by no means the only or most important. Also discussed in this paper are features such as(More)
Most deep architectures for image classification-even those that are trained to classify a large number of diverse categories-learn shared image representations with a single model. Intuitively, however, categories that are more similar should share more information than those that are very different. While hierarchical deep networks address this problem by(More)
The mechanical properties of Nitinol stents are normally evaluated experimentally due to complexities resulting from large deformations and material nonlinearity. Despite the difficulties associated with Finite Element Analysis (FEA), the success of the computational analysis in combination with experimental study leads to better understanding of stent(More)
Both the superelastic and the shape memory properties of the cubic NiTi alloy known as Nitinol arise from two-phase transitions; from a simple cubic austenite phase to a trigonal R-phase and to a lower symmetry martensite phase. In this article, we speculate that two competing forces drive these transitions. One is “mechanical” in nature and it takes the(More)
  • 1